diff --git "a/persadian_14B_GRPO.gguf" "b/persadian_14B_GRPO.gguf"
new file mode 100644--- /dev/null
+++ "b/persadian_14B_GRPO.gguf"
@@ -0,0 +1,10404 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "j_qKGkVHG4en"
+ },
+ "outputs": [],
+ "source": [
+ "%%capture\n",
+ "# Skip restarting message in Colab\n",
+ "import sys; modules = list(sys.modules.keys())\n",
+ "for x in modules: sys.modules.pop(x) if \"PIL\" in x or \"google\" in x else None\n",
+ "\n",
+ "!pip install \"unsloth==2025.2.4\" vllm\n",
+ "!pip install --upgrade pillow\n",
+ "# If you are running this notebook on local, you need to install `diffusers` too\n",
+ "# !pip install diffusers\n",
+ "# Temporarily install a specific TRL nightly version\n",
+ "!pip install git+https://github.com/huggingface/trl.git@e95f9fb74a3c3647b86f251b7e230ec51c64b72b"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "9QhPdli-HTDP",
+ "outputId": "67237161-128e-409f-bdac-d24619826959"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Unsloth: Patching Xformers to fix some performance issues.\n",
+ "π¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+ "π¦₯ Unsloth Zoo will now patch everything to make training faster!\n",
+ "INFO 02-17 08:54:08 __init__.py:190] Automatically detected platform cuda.\n"
+ ]
+ }
+ ],
+ "source": [
+ "from unsloth import FastLanguageModel, PatchFastRL\n",
+ "PatchFastRL(\"GRPO\", FastLanguageModel)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000,
+ "referenced_widgets": [
+ "f6cdfd55751c4b25bba036f935ab3f07",
+ "6c7fd7892301407a8b2ec47c3de4147f",
+ "be28b976f3454f1fac9cf7fa550d7025",
+ "36e49fb358c649eba9385aabf40bd002",
+ "481ff3d0e7784013aa69552ba2cb112d",
+ "fe95bd8bdff445f985b9d2c5f41f8602",
+ "3c4608e1efcc4c26af345bcd76ae6314",
+ "8015a02f160b4369b4382a13c0d155a2",
+ "3f19b40a2f294420b8ad741e33ceb7d4",
+ "b04e78369a8044e8b9a056f963461f4b",
+ "b96661e411eb474f809ca15789de914b",
+ "4b50e8e72406478a93d86825e255e580",
+ "f13a7454f09244b990e8a801242f30c5",
+ "c3714ffbb83f44f99236a7274d833528",
+ "b622ce7659e840efb495bebf4f7d0c8d",
+ "dfd56e4bcf554e45a09a1b05aff1c1ab",
+ "23c48ba794634d9ab72764008ec4ce62",
+ "e09e92afa3a54f8e986e816206dd5b08",
+ "d193009eb88e4cb7aae5337bdd35379e",
+ "6dde6c2c25f049c5b8d6dfdbd22bc752",
+ "09b9a7b158c94a3bb32f4c292727e39f",
+ "c336adfe2a774a88abfb6177adebc4de",
+ "aac912a5d0b343ff8eee265f49acda2f",
+ "8a6d772c4b6f4df3ac90ce7dc210c0af",
+ "6ad9f2392c9a4d9b83e3818685e10f37",
+ "4c2f698852304c989aa440a3ccb30079",
+ "3e4c00cdd5404a4f8f2a3e0978287ded",
+ "c6eeda8dabdc4ed6879f21849f7acdcb",
+ "4ae91de48fa64f3589327abeb4c42fea",
+ "7097460be2bc4243823f03d0d3c7b444",
+ "9bc992eba8a74f669b28d7d952a73a90",
+ "a4643bd78a2b4d8d95e2e08b325df6c7",
+ "ff91b6b814f04d2599a8cb7c640f7c95",
+ "15de40f79263474ca473b0494ac171a5",
+ "f26d39fde70049349911f409a41debb9",
+ "7d2eb02eda06476fbe165bd91d3ec0de",
+ "f9dfc691492d45aaaf788ae227034b35",
+ "03c5239792d942fbb9077fa9a5b15e92",
+ "e32ccfeea9a34d2ebae6b358be9a66ef",
+ "7ad16a66bbf741a789f6625d4fcc023f",
+ "947bd19136174b758959833a0f969407",
+ "7884fc70984b4479abb473f14de99409",
+ "b3058e3e8f90493793ae31ea7f42572a",
+ "102e6e7e53524fdeb3d4020ad6abcfe4",
+ "534f66ec60a2491db378b1239deb42ef",
+ "a4598817e02540feb95eca13aa3d1008",
+ "c1b56a556e684b38a9c78d43d4edad28",
+ "011cfb402b6143e9bf97bf83ab9422d9",
+ "09860d09e5ae489383ef6a099ed4bca3",
+ "65ae205166744508898dc82a16e7cc04",
+ "b3aa050d017d4a5a9bdd962f98736b24",
+ "c843aee0a4af4372876f1b66ae788617",
+ "1ee3e07aaa684199b4c34b5b6469a60c",
+ "c149b7f039fb45538e98222eaad21fc3",
+ "95315475337b45d699c4a56e6ff44136",
+ "a72e220f7033480e8a59ad6a1b04337b",
+ "db4a105befac44b69813fa2a641280b7",
+ "f13745853f8f4f98b88179a13057cd5c",
+ "b2ee0e317f0349b694502c395e0031a0",
+ "5141a74bb0d840e288c80cdad2fab75c",
+ "9241d465f6104fbb8c36be352265238f",
+ "53c007717fc043d4a64c9e9fa077fffd",
+ "df3c5b477d2d4a03a3436c1becf61e0f",
+ "46c726097cc840a5b61af5559cc1af4c",
+ "7fe26c30386f44d3a656132b6aded2fd",
+ "a1f928630ff54048afaf2f31783bfbd1",
+ "f72c52ac4b4d48ae937585b0413b92b4",
+ "99f8305417d046c1a14b6f6917b617fe",
+ "45cdaabb1a25494da00671d8a61cca02",
+ "bd1957ea932d4365b314044dbcc904f7",
+ "2eb96730c5ec4bc6abbc4e6fde479904",
+ "112b11adf39344558b2dbc62b2f2c34e",
+ "268a421a0ce348c6a0221dabf2aab752",
+ "7b44f7389e374bc496a71a43f31f9a93",
+ "c616b6c74fa54db281d51621c0956afb",
+ "40e919a3a8424396b29817cfac983a19",
+ "c352b23d93ea481c9db8989435987387",
+ "898310a70e1a41c6a78db36b15872139",
+ "26fe07f543a2443b9718c9bcfd4c7cef",
+ "3a65a0c044374eae8d1b52ea616c6966",
+ "6d245e8636004060ae64fc6b4b66dc4a",
+ "75e69c2aef4247b0b8483f339074e4b2",
+ "7250f0abd0dc4a8ca3c22283b9b95196",
+ "cac1c352fe3242e3876792d8cf8e152b",
+ "904a33f29a2d4a3bb91509200bce9ae8",
+ "1ecd9be8e8a24f88aaed902fc2184eac",
+ "ccb430e8f704472e9c57205516bdcb2d",
+ "798afe127b084fe0a91d17ada5f43100",
+ "8f0a82cfc58a4e5aa4d627c3617e3f3c",
+ "7c88f888c58b4983b32511fff78106f8",
+ "a41bb3352ea64ec6ad5c28f8fe0e4551",
+ "bcfa74c9f55a405aa7cc38264b446306",
+ "9a157adf02b44e549aa462862ab56efc",
+ "decddbf4eaa14c98ae66c47afc97ca45",
+ "d63a25bdfda24843a2650f1856f4f69c",
+ "b757336bb39649d38554d6ef46bc2256",
+ "a3b20c6c461e481ab7b3c5df55274d91",
+ "65d8ca0e51c544fdaaacc32f1acbf3fe",
+ "ccc94bb9f682477586ab5629a97fc6a4",
+ "95d2323a7f1943b79f617f9b8ea2a6da",
+ "af9563ee1ec84bf0badf7b85de531e0c",
+ "394dc8bcbd3349c0afcf622d4e2a5fd9",
+ "9f48cf0aca80435f89ec30c72f3393ba",
+ "137feb39a3e943b3823018f328c63cbe",
+ "f49ebeaf150c4a72b0d86218e5ff4850",
+ "8991569c58ab413c98416c05bc79f2d9",
+ "7b6fe5895b7249b7a8c9af48723ffcb2",
+ "50d2e33de27443e4b66b78c7edb02865",
+ "f529590d62b54546acf21e6e6954ada7",
+ "bf64273a481447c6ab170b58c038370e",
+ "8054c7c25be44345a5f93fc1041ef6aa",
+ "e9dea3d189c64987b70a2b993138a5b8",
+ "88f7bc62bba74221a9bfd1d64b59927e",
+ "0e2a50c346164248b83991be238df301",
+ "dadba4e34cb74ca98ab9b25bbaae4f97",
+ "d111bd033f984e248c035fe294a873cd",
+ "1ac166a037234cdab5fe781951e17d9a",
+ "189b3a15851948e5a668b76570dc9298",
+ "c163230a1ab549bda6ee48d17f1f25f8",
+ "0623fb8426f9490199431d16730827d8",
+ "df18562664e6464b877627df1c881f9e",
+ "fa6c3f077e46489897d00052dc9fa748",
+ "8715b1eb6d45493f975ae7edae037f85",
+ "9d262bb6433840f8aded127518a84658",
+ "138acd329cd14a9a9b3f80bd2b0e7221",
+ "dfb878bea074453fa4420bcd0adf419d",
+ "022e0ee46e124805be1fcbf38546bd56",
+ "1160e67aacb7462e9a629aeeec5e3d86",
+ "b71100db84c545da9a7049e3479cf0e1",
+ "138e3ee362eb49a48e7f4c3a82d505fd",
+ "2da48d73f0d24befa001bd8ce83564e9",
+ "053df1a83af249e0b4a2a1d7d8f7b656",
+ "b2f4bcc18a7c4a999dace66601368a02",
+ "3982c5c4a1e7497f9645e3f52aecf2b5",
+ "5f88d3f1cc26462aa57c5abe6653d2b2",
+ "b4487ca6b8b64d09ace434c23c786391",
+ "304abe1703954d32a9b38dc16c6c9b2a",
+ "1b6ec3d23a3e43c3b027a7882ffa68ff",
+ "d724e1316a7149b8b9c1c1f0a09fd78a",
+ "a297ec50c313419380e563823557e7d7",
+ "8eeedd15a5a94290ae0cb9a97f6a05f2",
+ "3c21343548944949bde672be75f55652",
+ "ac09b943e8444a8db305053b36da20d6",
+ "2fdedcfc3c27456ca35f6d1346605b41",
+ "20d5635fb1084f5fa2a093ae07b92a93",
+ "2b6e4cd7dfba4dafaedcd23bdecf1a83",
+ "3497f075cf834fbdafa9a93614e8a0e8",
+ "5ed334a793d346df9fd82789d03d1081",
+ "ccdd7ba41f214995ad302911ced5cc5e",
+ "2cccb494761b478781129aad28f475c7",
+ "e0e7827aea4f4a7e9d9e31a01e44b9cc",
+ "e0b71444938347a8a9d023d1e9a31b0b",
+ "2f0d9d575f724badb3c20df69cedec5a",
+ "edce818ad915499bb268f5072fd51712",
+ "3e0ebb372f3e4217a5483367f9b6ff7b",
+ "e467dcde83854d889ef02e2c7549c914",
+ "2481bdc4e0ab4e9a8868d9d3d998a733",
+ "6a1c470af59e4568b3e23cba91eb9ac0",
+ "573f0bb6bcbc4af8a1703277316cf572",
+ "79f47fbfccbb4fa88358df6fe018d4c9",
+ "da57411861e9458893bb1c3aa39c1d4f",
+ "d5d6dca20c874a8eb7bff7871712e6d8",
+ "1cfd941419c644f48a7a7abd19dc1a5a",
+ "a5eec47d513945f3a253b177e0a35728",
+ "a1ce8099c7384797bde75e1f6db8f3be",
+ "c340a432936344d9ad48b09ea3eb629c",
+ "9489548ea7144b8ca8ceeeac5aff2229",
+ "f0b50d31dfaf46a3978deaec21e07d3c",
+ "cc4dc41f111f493796ec6e12af0828bc",
+ "0b4326b140274671afe106409e7396ff",
+ "62931487994b45d38e3be0c27916ac03",
+ "71b6557b3e294946895dc7cb37a8696d",
+ "c2c396e31cec4ae1b374e06c979abadf",
+ "dfad1aac01a5423883dea57385827a35",
+ "d64fefcc50b64da0bd2349928fb182ab",
+ "677baf0c62774d6598e035e5d24a2d00"
+ ]
+ },
+ "id": "N4GKdbTRHUbf",
+ "outputId": "cc70020a-2c5d-4d2f-eb02-8f471ac84eb3"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Unsloth: Switching from Unsloth dynamic quant to normal quant since\n",
+ "we do not yet support fast inference for unsloth/phi-4-unsloth-bnb-4bit\n",
+ "==((====))== Unsloth 2025.2.4: Fast Llama patching. Transformers: 4.48.3.\n",
+ " \\\\ /| GPU: Tesla T4. Max memory: 14.741 GB. Platform: Linux.\n",
+ "O^O/ \\_/ \\ Torch: 2.5.1+cu124. CUDA: 7.5. CUDA Toolkit: 12.4. Triton: 3.1.0\n",
+ "\\ / Bfloat16 = FALSE. FA [Xformers = 0.0.28.post3. FA2 = False]\n",
+ " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n",
+ "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "config.json: 0%| | 0.00/1.40k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "f6cdfd55751c4b25bba036f935ab3f07"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Unsloth: vLLM loading unsloth/phi-4-bnb-4bit with actual GPU utilization = 69.52%\n",
+ "Unsloth: Your GPU has CUDA compute capability 7.5 with VRAM = 14.74 GB.\n",
+ "Unsloth: Using conservativeness = 1.0. Chunked prefill tokens = 512. Num Sequences = 128.\n",
+ "Unsloth: vLLM's KV Cache can use up to 0.28 GB. Also swap space = 2 GB.\n",
+ "WARNING 02-17 08:54:35 config.py:2386] Casting torch.bfloat16 to torch.float16.\n",
+ "INFO 02-17 08:54:48 config.py:542] This model supports multiple tasks: {'reward', 'generate', 'embed', 'classify', 'score'}. Defaulting to 'generate'.\n",
+ "Unsloth: vLLM Bitsandbytes config using kwargs = {'load_in_8bit': False, 'load_in_4bit': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'llm_int8_skip_modules': ['lm_head', 'multi_modal_projector', 'merger', 'modality_projection'], 'llm_int8_threshold': 6.0}\n",
+ "INFO 02-17 08:54:49 llm_engine.py:234] Initializing a V0 LLM engine (v0.7.2) with config: model='unsloth/phi-4-bnb-4bit', speculative_config=None, tokenizer='unsloth/phi-4-bnb-4bit', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.float16, max_seq_len=512, download_dir=None, load_format=LoadFormat.BITSANDBYTES, tensor_parallel_size=1, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=bitsandbytes, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda:0, decoding_config=DecodingConfig(guided_decoding_backend='xgrammar'), observability_config=ObservabilityConfig(otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=0, served_model_name=unsloth/phi-4-bnb-4bit, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=True, chunked_prefill_enabled=False, use_async_output_proc=True, disable_mm_preprocessor_cache=False, mm_processor_kwargs=None, pooler_config=None, compilation_config={\"level\":0,\"splitting_ops\":[],\"compile_sizes\":[],\"cudagraph_capture_sizes\":[128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],\"max_capture_size\":128}, use_cached_outputs=False, \n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "tokenizer_config.json: 0%| | 0.00/18.0k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "4b50e8e72406478a93d86825e255e580"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "vocab.json: 0%| | 0.00/1.61M [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "aac912a5d0b343ff8eee265f49acda2f"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "merges.txt: 0%| | 0.00/917k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "15de40f79263474ca473b0494ac171a5"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "tokenizer.json: 0%| | 0.00/7.15M [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "534f66ec60a2491db378b1239deb42ef"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "special_tokens_map.json: 0%| | 0.00/570 [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "a72e220f7033480e8a59ad6a1b04337b"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "generation_config.json: 0%| | 0.00/170 [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "f72c52ac4b4d48ae937585b0413b92b4"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "INFO 02-17 08:54:56 cuda.py:179] Cannot use FlashAttention-2 backend for Volta and Turing GPUs.\n",
+ "INFO 02-17 08:54:56 cuda.py:227] Using XFormers backend.\n",
+ "INFO 02-17 08:54:57 model_runner.py:1110] Starting to load model unsloth/phi-4-bnb-4bit...\n",
+ "INFO 02-17 08:54:58 loader.py:1102] Loading weights with BitsAndBytes quantization. May take a while ...\n",
+ "INFO 02-17 08:54:59 weight_utils.py:252] Using model weights format ['*.safetensors']\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "model-00001-of-00002.safetensors: 0%| | 0.00/4.98G [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "898310a70e1a41c6a78db36b15872139"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "model-00002-of-00002.safetensors: 0%| | 0.00/4.11G [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "8f0a82cfc58a4e5aa4d627c3617e3f3c"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Loading safetensors checkpoint shards: 0% Completed | 0/2 [00:00, ?it/s]\n"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "95d2323a7f1943b79f617f9b8ea2a6da"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Loading safetensors checkpoint shards: 0% Completed | 0/2 [00:00, ?it/s]\n"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "8054c7c25be44345a5f93fc1041ef6aa"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "INFO 02-17 08:58:54 model_runner.py:1115] Loading model weights took 8.4920 GB\n",
+ "INFO 02-17 08:58:55 punica_selector.py:18] Using PunicaWrapperGPU.\n",
+ "INFO 02-17 08:59:07 worker.py:267] Memory profiling takes 11.96 seconds\n",
+ "INFO 02-17 08:59:07 worker.py:267] the current vLLM instance can use total_gpu_memory (14.74GiB) x gpu_memory_utilization (0.70) = 10.25GiB\n",
+ "INFO 02-17 08:59:07 worker.py:267] model weights take 8.49GiB; non_torch_memory takes 0.05GiB; PyTorch activation peak memory takes 0.47GiB; the rest of the memory reserved for KV Cache is 1.24GiB.\n",
+ "INFO 02-17 08:59:08 executor_base.py:110] # CUDA blocks: 406, # CPU blocks: 655\n",
+ "INFO 02-17 08:59:08 executor_base.py:115] Maximum concurrency for 512 tokens per request: 12.69x\n",
+ "INFO 02-17 08:59:09 model_runner.py:1434] Capturing cudagraphs for decoding. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI. If out-of-memory error occurs during cudagraph capture, consider decreasing `gpu_memory_utilization` or switching to eager mode. You can also reduce the `max_num_seqs` as needed to decrease memory usage.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Capturing CUDA graph shapes: 100%|ββββββββββ| 19/19 [00:39<00:00, 2.10s/it]"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "INFO 02-17 08:59:49 model_runner.py:1562] Graph capturing finished in 40 secs, took 0.64 GiB\n",
+ "INFO 02-17 08:59:49 llm_engine.py:431] init engine (profile, create kv cache, warmup model) took 54.61 seconds\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "tokenizer_config.json: 0%| | 0.00/18.0k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "fa6c3f077e46489897d00052dc9fa748"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "vocab.json: 0%| | 0.00/1.61M [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "b2f4bcc18a7c4a999dace66601368a02"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "merges.txt: 0%| | 0.00/917k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "2fdedcfc3c27456ca35f6d1346605b41"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "special_tokens_map.json: 0%| | 0.00/570 [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "3e0ebb372f3e4217a5483367f9b6ff7b"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "tokenizer.json: 0%| | 0.00/7.15M [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "c340a432936344d9ad48b09ea3eb629c"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Not an error, but Unsloth cannot patch Attention layers with our manual autograd engine since either LoRA adapters\n",
+ "are not enabled or a bias term (like in Qwen) is used.\n",
+ "Not an error, but Unsloth cannot patch O projection layer with our manual autograd engine since either LoRA adapters\n",
+ "are not enabled or a bias term (like in Qwen) is used.\n",
+ "Unsloth 2025.2.4 patched 40 layers with 0 QKV layers, 0 O layers and 40 MLP layers.\n"
+ ]
+ }
+ ],
+ "source": [
+ "from unsloth import is_bfloat16_supported\n",
+ "import torch\n",
+ "max_seq_length = 512 # Can increase for longer reasoning traces\n",
+ "lora_rank = 16 # Larger rank = smarter, but slower\n",
+ "\n",
+ "model, tokenizer = FastLanguageModel.from_pretrained(\n",
+ " model_name = \"unsloth/Phi-4\",\n",
+ " max_seq_length = max_seq_length,\n",
+ " load_in_4bit = True, # False for LoRA 16bit\n",
+ " fast_inference = True, # Enable vLLM fast inference\n",
+ " max_lora_rank = lora_rank,\n",
+ " gpu_memory_utilization = 0.7, # Reduce if out of memory\n",
+ ")\n",
+ "\n",
+ "model = FastLanguageModel.get_peft_model(\n",
+ " model,\n",
+ " r = lora_rank, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128\n",
+ " target_modules = [\"gate_proj\", \"up_proj\", \"down_proj\",],\n",
+ " lora_alpha = lora_rank,\n",
+ " use_gradient_checkpointing = \"unsloth\", # Enable long context finetuning\n",
+ " random_state = 3407,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 871,
+ "referenced_widgets": [
+ "07b30751d3f3444d835031a204bdb2e0",
+ "3e0103dfdf38443ba43aeaf6abdf3265",
+ "db42a3d5b00d4024ac55ab1889a66fb9",
+ "458a05b30f2c476698e58df1d8924acb",
+ "13b27280a90041a883df4f0bfc2f9cd2",
+ "ffe6fa7a932d47c6a3eb9530cd37d446",
+ "5e6a16df45884d02a69cb6c18d895c50",
+ "10c0a63663144971b236882975b1ca8e",
+ "6e7e2cfc6f734f05832f49e1e60ae03e",
+ "bcddf8f0866347868641450c62bc1957",
+ "edfa5c630d234c0d914de21682e5d888",
+ "c2ce21915c9c4b4588080c48986a5e17",
+ "d871c30fbc0a4320ba212f2b90961390",
+ "ea7e8a0625a4469e911acb4f527f0f7e",
+ "0647391c490e4d4a9e5d248e12524c39",
+ "33f7f164af0843438941cb65d3413be1",
+ "6ae9e5c88f754e6196c1f443b3adfa21",
+ "28a2b6bbaf564e4f91b20931987dd27b",
+ "199355ae41414756b27f6dbc2ba5620d",
+ "60663929460c484eb466f232784e711c",
+ "962fbde200684096aeb69efde0c7ab57",
+ "31ef4562f7774dca949205c5562a2149",
+ "916effa56405485ea8a43e47669d9035",
+ "3d60fd796c8b443cba248de98a80e8c4",
+ "58b4d0041fde48a38d2d6555a4c3e95a",
+ "2bfa3f7520df46f49c749de3e8002926",
+ "7668c14dc1904018b9726103f5b92511",
+ "ffb4335d274d449dbcbee2d6aea8dbfb",
+ "f89d5dae5006481191f7123b19eb4d3e",
+ "6d8a85478b0b4424a84a389851df6554",
+ "91628b0f3801439989d6014cace043cc",
+ "dfa4fc6f471f4027ad87ae865c49da5e",
+ "2f706a61e19547d7a0ae53cc96227eb2",
+ "eb107bdd4867400d99dfe332a190a419",
+ "ab4dfebe8d2948bba5e4ada27a543944",
+ "7c91e824950d4fe0bf3f5b8c4d803274",
+ "3e06a676bde54989918fd2e553fc0bac",
+ "a17709ae6e7646719ba80a40627286f9",
+ "204c4ad9ed2d45c8a9b148e061a46ffa",
+ "2dfdf4441b104abc87683488a43cd4c7",
+ "d1ce3b6a25034044b61a7d4d4f81b1a2",
+ "8b72be4ef1054194978a4222155fbc56",
+ "64d8c1496ae14364a51fa4127f42ff71",
+ "9efcb1c8f86040dab38c969773229a4f",
+ "7a4ba2775ea042c09440feda17af8547",
+ "80687fd47d114b94972671535162df18",
+ "f217fde868194c88a9bcf25cf68da353",
+ "c5c423ff63f84780a65e9871c4b16b54",
+ "ddeccde7c52c4f3e99e25f5713a2bd30",
+ "b1c1d47ce3a447c5b566aac8293ee920",
+ "472011119aa8443082082f32e5cdcead",
+ "dbf87fa697f64c939953d5ee43c3451d",
+ "edd877fc1cec47c79a7bfc66353878f6",
+ "3a78e3ab794f4171a1f5340ae6bb3463",
+ "c2d385cb15f245fbbfe997ee9521ebcb",
+ "786a033ddff343288d53cd29436e1c6e",
+ "ff97c955f459472ead1d7a0855d7db6e",
+ "8e015ff487584563b4af1cde693e9ad2",
+ "94ea5740d07f4ae1abd2f494aed82ede",
+ "b992b5106cb14b9e8c01883d303203a0",
+ "d0c02c0ed31b4c3fbb0244b4be2f703a",
+ "0575d12e030e40beabba0b4c53e843c7",
+ "c7e27fcad0724914877fbef99d2ee498",
+ "ff8d48a49166403caafbb9971588bee5",
+ "fd4ef85c288a40f1a2beb1097a798909",
+ "3cf01e74e4964cf8b5347c6f517e05f4"
+ ]
+ },
+ "id": "J8F1s_dENB3N",
+ "outputId": "0fd3c575-54a5-4558-869f-4fe663ccd865"
+ },
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "README.md: 0%| | 0.00/7.94k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "07b30751d3f3444d835031a204bdb2e0"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "train-00000-of-00001.parquet: 0%| | 0.00/2.31M [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "c2ce21915c9c4b4588080c48986a5e17"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "test-00000-of-00001.parquet: 0%| | 0.00/419k [00:00, ?B/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "916effa56405485ea8a43e47669d9035"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Generating train split: 0%| | 0/7473 [00:00, ? examples/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "eb107bdd4867400d99dfe332a190a419"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Generating test split: 0%| | 0/1319 [00:00, ? examples/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "7a4ba2775ea042c09440feda17af8547"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Map: 0%| | 0/7473 [00:00, ? examples/s]"
+ ],
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "786a033ddff343288d53cd29436e1c6e"
+ }
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Prompt: [{'content': '\\nRespond in the following format:\\n\\n...\\n\\n\\n...\\n\\n', 'role': 'system'}, {'content': 'Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?', 'role': 'user'}]\n",
+ "Answer: 72\n",
+ "Reasoning: \n",
+ "To solve the problem, let's break it down step by step:\n",
+ "\n",
+ "1. **Understand the problem**: Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?\n",
+ "2. **Identify the key components**: [Explain the key components of the problem here.]\n",
+ "3. **Perform calculations**: [Show the calculations or logical steps here.]\n",
+ "4. **Verify the solution**: [Double-check the calculations or logic to ensure correctness.]\n",
+ "\n",
+ "Based on the above steps, the answer is derived as follows:\n",
+ "\n",
+ "\n",
+ "72\n",
+ "\n",
+ "-------------------- Question:\n",
+ "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? \n",
+ "Answer:\n",
+ "72 \n",
+ "Response:\n",
+ "\n",
+ "To solve the problem, let's break it down step by step:\n",
+ "\n",
+ "1. **Understand the problem**: Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?\n",
+ "2. **Identify the key components**: [Explain the key components of the problem here.]\n",
+ "3. **Perform calculations**: [Show the calculations or logical steps here.]\n",
+ "4. **Verify the solution**: [Double-check the calculations or logic to ensure correctness.]\n",
+ "\n",
+ "Based on the above steps, the answer is derived as follows:\n",
+ "\n",
+ "\n",
+ "72\n",
+ " \n",
+ "Extracted:\n",
+ "72\n",
+ "Correctness Reward: [2.0]\n",
+ "Format Reward: [0.0]\n"
+ ]
+ }
+ ],
+ "source": [
+ "import re\n",
+ "from datasets import load_dataset, Dataset\n",
+ "\n",
+ "# Load and prep dataset\n",
+ "SYSTEM_PROMPT = \"\"\"\n",
+ "Respond in the following format:\n",
+ "\n",
+ "...\n",
+ "\n",
+ "\n",
+ "...\n",
+ "\n",
+ "\"\"\"\n",
+ "\n",
+ "XML_COT_FORMAT = \"\"\"\\\n",
+ "\n",
+ "{reasoning}\n",
+ "\n",
+ "\n",
+ "{answer}\n",
+ "\n",
+ "\"\"\"\n",
+ "\n",
+ "def extract_xml_answer(text: str) -> str:\n",
+ " answer = text.split(\"\")[-1]\n",
+ " answer = answer.split(\"\")[0]\n",
+ " return answer.strip()\n",
+ "\n",
+ "def extract_hash_answer(text: str) -> str | None:\n",
+ " if \"####\" not in text:\n",
+ " return None\n",
+ " return text.split(\"####\")[1].strip()\n",
+ "\n",
+ "def generate_reasoning(question: str, answer: str) -> str:\n",
+ " \"\"\"\n",
+ " Generates reasoning for a given question and answer in the specified XML format.\n",
+ " \"\"\"\n",
+ " reasoning = f\"\"\"\n",
+ "\n",
+ "To solve the problem, let's break it down step by step:\n",
+ "\n",
+ "1. **Understand the problem**: {question}\n",
+ "2. **Identify the key components**: [Explain the key components of the problem here.]\n",
+ "3. **Perform calculations**: [Show the calculations or logical steps here.]\n",
+ "4. **Verify the solution**: [Double-check the calculations or logic to ensure correctness.]\n",
+ "\n",
+ "Based on the above steps, the answer is derived as follows:\n",
+ "\n",
+ "\n",
+ "{answer}\n",
+ "\n",
+ "\"\"\"\n",
+ " return reasoning.strip()\n",
+ "\n",
+ "# Load dataset with reasoning\n",
+ "def get_gsm8k_with_reasoning(split=\"train\") -> Dataset:\n",
+ " data = load_dataset('openai/gsm8k', 'main')[split] # type: ignore\n",
+ " data = data.map(lambda x: { # type: ignore\n",
+ " 'prompt': [\n",
+ " {'role': 'system', 'content': SYSTEM_PROMPT},\n",
+ " {'role': 'user', 'content': x['question']}\n",
+ " ],\n",
+ " 'answer': extract_hash_answer(x['answer']),\n",
+ " 'reasoning': generate_reasoning(x['question'], extract_hash_answer(x['answer']))\n",
+ " }) # type: ignore\n",
+ " return data # type: ignore\n",
+ "\n",
+ "dataset = get_gsm8k_with_reasoning()\n",
+ "\n",
+ "# Reward functions\n",
+ "def correctness_reward_func(prompts, completions, answer, **kwargs) -> list[float]:\n",
+ " responses = [completion['content'] for completion in completions] # Access 'content' directly from the dictionary\n",
+ " q = prompts[0][-1]['content']\n",
+ " extracted_responses = [extract_xml_answer(r) for r in responses]\n",
+ " print('-' * 20, f\"Question:\\n{q}\", f\"\\nAnswer:\\n{answer[0]}\", f\"\\nResponse:\\n{responses[0]}\", f\"\\nExtracted:\\n{extracted_responses[0]}\")\n",
+ " return [2.0 if r == a else 0.0 for r, a in zip(extracted_responses, answer)]\n",
+ "\n",
+ "def int_reward_func(completions, **kwargs) -> list[float]:\n",
+ " # completions is a list of dictionaries, access 'content' directly\n",
+ " responses = [completion[\"content\"] for completion in completions]\n",
+ " extracted_responses = [extract_xml_answer(r) for r in responses]\n",
+ " return [0.5 if r.isdigit() else 0.0 for r in extracted_responses]\n",
+ "\n",
+ "def strict_format_reward_func(completions, **kwargs) -> list[float]:\n",
+ " \"\"\"Reward function that checks if the completion has a specific format.\"\"\"\n",
+ " pattern = r\"^\\n.*?\\n\\n\\n.*?\\n\\n$\"\n",
+ " # completions is a list of dictionaries, access 'content' directly\n",
+ " responses = [completion[\"content\"] for completion in completions]\n",
+ " matches = [re.match(pattern, r) for r in responses]\n",
+ " return [0.5 if match else 0.0 for match in matches]\n",
+ "\n",
+ "def soft_format_reward_func(completions, **kwargs) -> list[float]:\n",
+ " \"\"\"Reward function that checks if the completion has a specific format.\"\"\"\n",
+ " pattern = r\".*?\\s*.*?\"\n",
+ " # completions is a list of dictionaries, access 'content' directly\n",
+ " responses = [completion[\"content\"] for completion in completions]\n",
+ " matches = [re.match(pattern, r) for r in responses]\n",
+ " return [0.5 if match else 0.0 for match in matches]\n",
+ "\n",
+ "def count_xml(text) -> float:\n",
+ " count = 0.0\n",
+ " if text.count(\"\\n\") == 1:\n",
+ " count += 0.125\n",
+ " if text.count(\"\\n\\n\") == 1:\n",
+ " count += 0.125\n",
+ " if text.count(\"\\n\\n\") == 1:\n",
+ " count += 0.125\n",
+ " count -= len(text.split(\"\\n\\n\")[-1]) * 0.001\n",
+ " if text.count(\"\\n\") == 1:\n",
+ " count += 0.125\n",
+ " count -= (len(text.split(\"\\n\")[-1]) - 1) * 0.001\n",
+ " return count\n",
+ "\n",
+ "def xmlcount_reward_func(completions, **kwargs) -> list[float]:\n",
+ " # completions is a list of dictionaries, access 'content' directly\n",
+ " contents = [completion[\"content\"] for completion in completions]\n",
+ " return [count_xml(c) for c in contents]\n",
+ "\n",
+ "# Example usage\n",
+ "if __name__ == \"__main__\":\n",
+ " # Print the first example from the dataset\n",
+ " example = dataset[0]\n",
+ " print(\"Prompt:\", example['prompt'])\n",
+ " print(\"Answer:\", example['answer'])\n",
+ " print(\"Reasoning:\", example['reasoning'])\n",
+ "\n",
+ " # Test reward functions\n",
+ " prompts = [example['prompt']]\n",
+ " completions = [{'role': 'assistant', 'content': example['reasoning']}]\n",
+ " answers = [example['answer']]\n",
+ "\n",
+ " print(\"Correctness Reward:\", correctness_reward_func(prompts, completions, answers))\n",
+ " print(\"Format Reward:\", strict_format_reward_func(completions))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "-_-xkav9OZ4S",
+ "outputId": "ffbe75bb-a6b4-4ee3-809a-0e68ca905801"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "torch.distributed process group is initialized, but parallel_mode != ParallelMode.DISTRIBUTED. In order to use Torch DDP, launch your script with `python -m torch.distributed.launch\n"
+ ]
+ }
+ ],
+ "source": [
+ "from trl import GRPOConfig, GRPOTrainer\n",
+ "training_args = GRPOConfig(\n",
+ " use_vllm = True, # use vLLM for fast inference!\n",
+ " learning_rate = 5e-6,\n",
+ " adam_beta1 = 0.9,\n",
+ " adam_beta2 = 0.99,\n",
+ " weight_decay = 0.1,\n",
+ " warmup_ratio = 0.1,\n",
+ " lr_scheduler_type = \"cosine\",\n",
+ " optim = \"paged_adamw_8bit\",\n",
+ " logging_steps = 1,\n",
+ " bf16 = is_bfloat16_supported(),\n",
+ " fp16 = not is_bfloat16_supported(),\n",
+ " per_device_train_batch_size = 1,\n",
+ " gradient_accumulation_steps = 1, # Increase to 4 for smoother training\n",
+ " num_generations = 6, # Decrease if out of memory\n",
+ " max_prompt_length = 256,\n",
+ " max_completion_length = 200,\n",
+ " # num_train_epochs = 1, # Set to 1 for a full training run\n",
+ " max_steps = 100,\n",
+ " save_steps = 250,\n",
+ " max_grad_norm = 0.1,\n",
+ " report_to = \"none\", # Can use Weights & Biases\n",
+ " output_dir = \"outputs\",\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "LX7n5tGJUAZS"
+ },
+ "outputs": [],
+ "source": [
+ "def reward_wrapper(reward_func):\n",
+ " \"\"\"Wraps a reward function to ensure it receives completions as a list of dictionaries.\"\"\"\n",
+ " def wrapped_reward_func(completions, **kwargs):\n",
+ " # Ensure completions is always a list of dictionaries\n",
+ " completions = [{'content': c} if isinstance(c, str) else c for c in completions]\n",
+ " # Check if each completion has a 'content' key before accessing it\n",
+ " completions = [c for c in completions if isinstance(c, dict) and 'content' in c]\n",
+ "\n",
+ " # Print the number of completions before applying the reward function\n",
+ " print(f\"Number of completions received by {reward_func.__name__}: {len(completions)}\")\n",
+ "\n",
+ " # Remove 'prompts' from kwargs if it exists to avoid conflict\n",
+ " kwargs.pop('prompts', None)\n",
+ "\n",
+ " rewards = reward_func(completions=completions, **kwargs) # Pass completions as keyword argument\n",
+ "\n",
+ " # Print the rewards returned by the reward function\n",
+ " print(f\"Rewards returned by {reward_func.__name__}: {rewards}\")\n",
+ "\n",
+ " # Ensure that the reward function returns a list of the correct length\n",
+ " if len(rewards) != training_args.num_generations:\n",
+ " print(f\"Warning: {reward_func.__name__} returned {len(rewards)} rewards, but {training_args.num_generations} were expected.\")\n",
+ " rewards = rewards + [0.0] * (training_args.num_generations - len(rewards)) # Pad with zeros if necessary\n",
+ "\n",
+ " return rewards\n",
+ " return wrapped_reward_func"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "NARzriInUl5n"
+ },
+ "outputs": [],
+ "source": [
+ "def reward_wrapper(reward_func):\n",
+ " \"\"\"Wraps a reward function to ensure it receives completions as a list of dictionaries.\"\"\"\n",
+ " def wrapped_reward_func(completions, **kwargs):\n",
+ " # Ensure completions is always a list of dictionaries\n",
+ " completions = [{'content': c} if isinstance(c, str) else c for c in completions]\n",
+ " # Check if each completion has a 'content' key before accessing it\n",
+ " completions = [c for c in completions if isinstance(c, dict) and 'content' in c]\n",
+ "\n",
+ " # Print the number of completions before applying the reward function\n",
+ " print(f\"Number of completions received by {reward_func.__name__}: {len(completions)}\")\n",
+ "\n",
+ " # Pass 'prompts' and 'answer' as keyword arguments if the reward function expects them\n",
+ " if reward_func.__name__ == 'correctness_reward_func':\n",
+ " rewards = reward_func(completions=completions, prompts=kwargs.get('prompts'), answer=kwargs.get('answer'))\n",
+ " else:\n",
+ " # Remove 'prompts' from kwargs if it exists to avoid conflict for other reward functions\n",
+ " kwargs.pop('prompts', None)\n",
+ " rewards = reward_func(completions=completions, **kwargs) # Pass completions as keyword argument\n",
+ "\n",
+ " # Print the rewards returned by the reward function\n",
+ " print(f\"Rewards returned by {reward_func.__name__}: {rewards}\")\n",
+ "\n",
+ " # Ensure that the reward function returns a list of the correct length\n",
+ " if len(rewards) != training_args.num_generations:\n",
+ " print(f\"Warning: {reward_func.__name__} returned {len(rewards)} rewards, but {training_args.num_generations} were expected.\")\n",
+ " rewards = rewards + [0.0] * (training_args.num_generations - len(rewards)) # Pad with zeros if necessary\n",
+ "\n",
+ " return rewards\n",
+ " return wrapped_reward_func"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "jULDjAvQVxP3"
+ },
+ "outputs": [],
+ "source": [
+ "def correctness_reward_func(prompts, completions, answer, **kwargs) -> list[float]:\n",
+ " \"\"\"\n",
+ " Calculates the correctness reward by comparing extracted answers with the ground truth.\n",
+ "\n",
+ " Args:\n",
+ " prompts: A list of dictionaries representing the prompts. Each dictionary should have a 'content' key.\n",
+ " completions: A list of dictionaries representing the completions. Each dictionary should have a 'content' key.\n",
+ " answer: A list or a string representing the correct answer.\n",
+ "\n",
+ " Returns:\n",
+ " A list of floats representing the correctness reward for each completion.\n",
+ " \"\"\"\n",
+ " responses = [completion['content'] for completion in completions]\n",
+ " q = prompts[0][-1]['content'] if prompts and prompts[0] and len(prompts[0]) > 0 and isinstance(prompts[0][-1], dict) and 'content' in prompts[0][-1] else '' # Access 'content' safely\n",
+ " extracted_responses = [extract_xml_answer(r) for r in responses]\n",
+ "\n",
+ " # Handle the case where answer is not a list or is empty\n",
+ " if not isinstance(answer, list) or not answer:\n",
+ " print(f\"Warning: answer is not a list or is empty: {answer}\")\n",
+ " return [0.0] * len(responses) # Return 0 reward for all responses if answer is invalid\n",
+ "\n",
+ " print('-' * 20, f\"Question:\\n{q}\", f\"\\nAnswer:\\n{answer[0]}\", f\"\\nResponse:\\n{responses[0]}\", f\"\\nExtracted:\\n{extracted_responses[0]}\")\n",
+ "\n",
+ " # Compare extracted responses with the correct answer (handling potential type mismatch)\n",
+ " return [2.0 if str(r) == str(a) else 0.0 for r, a in zip(extracted_responses, answer)]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "yRvRs00zY35v"
+ },
+ "outputs": [],
+ "source": [
+ "def reward_wrapper(reward_func):\n",
+ " \"\"\"Wraps a reward function to ensure it receives completions as a list of dictionaries.\"\"\"\n",
+ " def wrapped_reward_func(completions, **kwargs):\n",
+ " # ... (Existing code) ...\n",
+ "\n",
+ " # Pass 'prompts' and 'answer' as keyword arguments if the reward function expects them\n",
+ " if reward_func.__name__ == 'correctness_reward_func':\n",
+ " # Ensure answer is a list and is not empty\n",
+ " answer = kwargs.get('answer')\n",
+ " if not isinstance(answer, list) or not answer:\n",
+ " print(f\"Warning: answer is not a list or is empty: {answer}. Returning 0 reward.\")\n",
+ " return [0.0] * training_args.num_generations\n",
+ "\n",
+ " rewards = reward_func(completions=completions, prompts=kwargs.get('prompts'), answer=answer)\n",
+ " # ... (Existing code) ...\n",
+ "\n",
+ " return rewards\n",
+ " return wrapped_reward_func"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "A_aJGQCkbTp0"
+ },
+ "outputs": [],
+ "source": [
+ "def reward_wrapper(reward_func):\n",
+ " \"\"\"Wraps a reward function to ensure it receives completions as a list of dictionaries.\"\"\"\n",
+ " def wrapped_reward_func(completions, **kwargs):\n",
+ " # ... (Existing code) ...\n",
+ "\n",
+ " # Pass 'prompts' and 'answer' as keyword arguments if the reward function expects them\n",
+ " if reward_func.__name__ == 'correctness_reward_func':\n",
+ " # Ensure answer is a list and is not empty\n",
+ " answer = kwargs.get('answer')\n",
+ " # This is the modified line to handle the string '72'\n",
+ " answer = [[answer[0]]] if isinstance(answer, list) and isinstance(answer[0], str) else answer\n",
+ " if not isinstance(answer, list) or not answer or not answer[0]: # Added check for answer[0]\n",
+ " print(f\"Warning: answer is not a list or is empty: {answer}. Returning 0 reward.\")\n",
+ " return [0.0] * training_args.num_generations\n",
+ "\n",
+ " rewards = reward_func(completions=completions, prompts=kwargs.get('prompts'), answer=answer)\n",
+ " # ... (Existing code) ...\n",
+ "\n",
+ " return rewards\n",
+ " return wrapped_reward_func"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 391
+ },
+ "collapsed": true,
+ "id": "wJ5T59VMOlci",
+ "outputId": "fe92be9f-3b80-4a44-9dce-d4cf56d2da1b"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n",
+ " \\\\ /| Num examples = 7,473 | Num Epochs = 1\n",
+ "O^O/ \\_/ \\ Batch size per device = 1 | Gradient Accumulation steps = 1\n",
+ "\\ / Total batch size = 1 | Total steps = 100\n",
+ " \"-____-\" Number of trainable parameters = 44,236,800\n"
+ ]
+ },
+ {
+ "output_type": "error",
+ "ename": "UnboundLocalError",
+ "evalue": "cannot access local variable 'rewards' where it is not associated with a value",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mUnboundLocalError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0mtrain_dataset\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m )\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m 2169\u001b[0m \u001b[0mhf_hub_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0menable_progress_bars\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2170\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2171\u001b[0;31m return inner_training_loop(\n\u001b[0m\u001b[1;32m 2172\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2173\u001b[0m \u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mresume_from_checkpoint\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/unsloth/models/llama.py\u001b[0m in \u001b[0;36m_fast_inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/unsloth/models/_utils.py\u001b[0m in \u001b[0;36m_unsloth_training_step\u001b[0;34m(self, model, inputs, num_items_in_batch)\u001b[0m\n",
+ "\u001b[0;32m/content/unsloth_compiled_cache/GRPOTrainer.py\u001b[0m in \u001b[0;36m_prepare_inputs\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 408\u001b[0m \u001b[0;31m# Repeat each value in the column for `num_generations` times\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 409\u001b[0m \u001b[0mreward_kwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mexample\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnum_generations\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 410\u001b[0;31m \u001b[0moutput_reward_func\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mreward_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprompts\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprompts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcompletions\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcompletions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mreward_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 411\u001b[0m \u001b[0mrewards_per_func\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_reward_func\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfloat32\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdevice\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 412\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m\u001b[0m in \u001b[0;36mwrapped_reward_func\u001b[0;34m(completions, **kwargs)\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0;31m# ... (Existing code) ...\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 18\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 19\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mrewards\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 20\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapped_reward_func\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mUnboundLocalError\u001b[0m: cannot access local variable 'rewards' where it is not associated with a value"
+ ]
+ }
+ ],
+ "source": [
+ "trainer = GRPOTrainer(\n",
+ " model=model,\n",
+ " processing_class=tokenizer,\n",
+ " reward_funcs=[\n",
+ " reward_wrapper(xmlcount_reward_func),\n",
+ " reward_wrapper(soft_format_reward_func),\n",
+ " reward_wrapper(strict_format_reward_func),\n",
+ " reward_wrapper(int_reward_func),\n",
+ " reward_wrapper(correctness_reward_func),\n",
+ " ],\n",
+ " args=training_args,\n",
+ " train_dataset=dataset,\n",
+ ")\n",
+ "trainer.train()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 90
+ },
+ "id": "_t67dEVofLbt",
+ "outputId": "a88a79ee-1b19-48c9-e792-878fdf700813"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Processed prompts: 100%|ββββββββββ| 1/1 [00:12<00:00, 12.71s/it, est. speed input: 1.65 toks/s, output: 10.15 toks/s]\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "\"9.11 is bigger than 9.9. When comparing decimal numbers, you look at the digits from left to right. Both numbers have a 9 before the decimal point, so you then compare the digits after the decimal point. The number 9.11 has a 1 in the tenths place, while 9.9 has a 9 in the tenths place. To make the comparison easier, you can think of 9.9 as 9.90. Now, it's clear that 9.11 (which is the same as 9.110) is greater than 9.90.\""
+ ],
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
+ }
+ },
+ "metadata": {},
+ "execution_count": 14
+ }
+ ],
+ "source": [
+ "text = tokenizer.apply_chat_template([\n",
+ " {\"role\" : \"user\", \"content\" : \"Which is bigger? 9.11 or 9.9?\"},\n",
+ "], tokenize = False, add_generation_prompt = True)\n",
+ "\n",
+ "from vllm import SamplingParams\n",
+ "sampling_params = SamplingParams(\n",
+ " temperature = 0.8,\n",
+ " top_p = 0.95,\n",
+ " max_tokens = 1024,\n",
+ ")\n",
+ "output = model.fast_generate(\n",
+ " [text],\n",
+ " sampling_params = sampling_params,\n",
+ " lora_request = None,\n",
+ ")[0].outputs[0].text\n",
+ "\n",
+ "output"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "G_YVFjW_fRz0"
+ },
+ "outputs": [],
+ "source": [
+ "model.save_lora(\"grpo_saved_lora\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 107
+ },
+ "id": "uhdb6ILIfZoE",
+ "outputId": "742b41e4-42ac-4863-9a5f-1bc35c10789c"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Processed prompts: 100%|ββββββββββ| 1/1 [00:17<00:00, 17.64s/it, est. speed input: 2.66 toks/s, output: 9.75 toks/s]\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "'\\nTo determine which number is bigger, we compare 9.11 and 9.9 by looking at their decimal values.\\n\\n1. **Compare the whole number part:** \\n Both numbers have the same whole number part, which is 9. So, we move to the decimal part.\\n\\n2. **Compare the tenths place:** \\n - 9.11 has a 1 in the tenths place.\\n - 9.9 has a 9 in the tenths place.\\n\\nSince 9 is greater than 1, 9.9 is already greater than 9.11 at this point, without needing to look further.\\n\\nTherefore, 9.9 is bigger than 9.11.\\n\\n\\n\\n9.9 is bigger than 9.11.\\n'"
+ ],
+ "application/vnd.google.colaboratory.intrinsic+json": {
+ "type": "string"
+ }
+ },
+ "metadata": {},
+ "execution_count": 16
+ }
+ ],
+ "source": [
+ "text = tokenizer.apply_chat_template([\n",
+ " {\"role\" : \"system\", \"content\" : SYSTEM_PROMPT},\n",
+ " {\"role\" : \"user\", \"content\" : \"Which is bigger? 9.11 or 9.9?\"},\n",
+ "], tokenize = False, add_generation_prompt = True)\n",
+ "\n",
+ "from vllm import SamplingParams\n",
+ "sampling_params = SamplingParams(\n",
+ " temperature = 0.8,\n",
+ " top_p = 0.95,\n",
+ " max_tokens = 1024,\n",
+ ")\n",
+ "output = model.fast_generate(\n",
+ " text,\n",
+ " sampling_params = sampling_params,\n",
+ " lora_request = model.load_lora(\"grpo_saved_lora\"),\n",
+ ")[0].outputs[0].text\n",
+ "\n",
+ "output"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "qhElZOhufg6j",
+ "outputId": "c62fbf16-a116-49bf-d24b-74ca7ea0ef17"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "\n",
+ "To determine which number is bigger, we compare 9.11 and 9.9 by looking at their decimal values.\n",
+ "\n",
+ "1. **Compare the whole number part:** \n",
+ " Both numbers have the same whole number part, which is 9. So, we move to the decimal part.\n",
+ "\n",
+ "2. **Compare the tenths place:** \n",
+ " - 9.11 has a 1 in the tenths place.\n",
+ " - 9.9 has a 9 in the tenths place.\n",
+ "\n",
+ "Since 9 is greater than 1, 9.9 is already greater than 9.11 at this point, without needing to look further.\n",
+ "\n",
+ "Therefore, 9.9 is bigger than 9.11.\n",
+ "\n",
+ "\n",
+ "\n",
+ "9.9 is bigger than 9.11.\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(output)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "9p7HYGydfrmT"
+ },
+ "outputs": [],
+ "source": [
+ "# Merge to 16bit\n",
+ "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_16bit\",)\n",
+ "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_16bit\", token = \"\")\n",
+ "\n",
+ "# Merge to 4bit\n",
+ "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_4bit\",)\n",
+ "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_4bit\", token = \"\")\n",
+ "\n",
+ "# Just LoRA adapters\n",
+ "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"lora\",)\n",
+ "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"lora\", token = \"\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "wmBOW1s8fwJT"
+ },
+ "outputs": [],
+ "source": [
+ "# Save to 8bit Q8_0\n",
+ "if False: model.save_pretrained_gguf(\"model\", tokenizer,)\n",
+ "# Remember to go to https://huggingface.co/settings/tokens for a token!\n",
+ "# And change hf to your username!\n",
+ "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, token = \"\")\n",
+ "\n",
+ "# Save to 16bit GGUF\n",
+ "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"f16\")\n",
+ "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"f16\", token = \"\")\n",
+ "\n",
+ "# Save to q4_k_m GGUF\n",
+ "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"q4_k_m\")\n",
+ "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"q4_k_m\", token = \"\")\n",
+ "\n",
+ "# Save to multiple GGUF options - much faster if you want multiple!\n",
+ "if False:\n",
+ " model.push_to_hub_gguf(\n",
+ " \"hf/model\", # Change hf to your username!\n",
+ " tokenizer,\n",
+ " quantization_method = [\"q4_k_m\", \"q8_0\", \"q5_k_m\",],\n",
+ " token = \"\",\n",
+ " )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "1HRg3gETkbzM",
+ "outputId": "db15d169-3f9e-4ecd-8854-39256cd97bfb"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Unsloth: You have 1 CPUs. Using `safe_serialization` is 10x slower.\n",
+ "We shall switch to Pytorch saving, which might take 3 minutes and not 30 minutes.\n",
+ "To force `safe_serialization`, set it to `None` instead.\n",
+ "Unsloth: Kaggle/Colab has limited disk space. We need to delete the downloaded\n",
+ "model which will save 4-16GB of disk space, allowing you to save on Kaggle/Colab.\n",
+ "Unsloth: Will remove a cached repo with size 9.1G\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Unsloth: Merging 4bit and LoRA weights to 16bit...\n",
+ "Unsloth: Will use up to 2.62 out of 12.67 RAM for saving.\n",
+ "Unsloth: Saving model... This might take 5 minutes ...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ " 8%|β | 3/40 [00:00<00:05, 6.98it/s]\n",
+ "We will save to Disk and not RAM now.\n",
+ "100%|ββββββββββ| 40/40 [13:22<00:00, 20.07s/it]\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Unsloth: Saving tokenizer... Done.\n",
+ "Unsloth: Saving persadian_14B-GRPO/pytorch_model-00001-of-00006.bin...\n",
+ "Unsloth: Saving persadian_14B-GRPO/pytorch_model-00002-of-00006.bin...\n",
+ "Unsloth: Saving persadian_14B-GRPO/pytorch_model-00003-of-00006.bin...\n",
+ "Unsloth: Saving persadian_14B-GRPO/pytorch_model-00004-of-00006.bin...\n",
+ "Unsloth: Saving persadian_14B-GRPO/pytorch_model-00005-of-00006.bin...\n",
+ "Unsloth: Saving persadian_14B-GRPO/pytorch_model-00006-of-00006.bin...\n",
+ "Done.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "Unsloth: Converting llama model. Can use fast conversion = False.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "==((====))== Unsloth: Conversion from QLoRA to GGUF information\n",
+ " \\\\ /| [0] Installing llama.cpp might take 3 minutes.\n",
+ "O^O/ \\_/ \\ [1] Converting HF to GGUF 16bits might take 3 minutes.\n",
+ "\\ / [2] Converting GGUF 16bits to ['q8_0'] might take 10 minutes each.\n",
+ " \"-____-\" In total, you will have to wait at least 16 minutes.\n",
+ "\n",
+ "Unsloth: Installing llama.cpp. This might take 3 minutes...\n",
+ "Unsloth: CMAKE detected. Finalizing some steps for installation.\n",
+ "Unsloth: [1] Converting model at persadian_14B-GRPO into q8_0 GGUF format.\n",
+ "The output location will be /content/persadian_14B-GRPO/unsloth.Q8_0.gguf\n",
+ "This might take 3 minutes...\n",
+ "INFO:hf-to-gguf:Loading model: persadian_14B-GRPO\n",
+ "INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n",
+ "INFO:hf-to-gguf:Exporting model...\n",
+ "INFO:hf-to-gguf:gguf: loading model weight map from 'pytorch_model.bin.index.json'\n",
+ "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model-00001-of-00006.bin'\n",
+ "INFO:hf-to-gguf:token_embd.weight, torch.float16 --> Q8_0, shape = {5120, 100352}\n",
+ "INFO:hf-to-gguf:blk.0.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.0.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.0.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.0.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.1.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.1.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.1.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.1.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.2.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.2.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.2.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.2.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.3.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.3.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.3.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.3.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.4.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.4.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.4.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.4.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.5.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.5.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.5.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.5.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model-00002-of-00006.bin'\n",
+ "INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.6.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.6.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.6.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.6.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.7.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.7.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.7.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.7.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.8.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.8.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.8.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.8.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.9.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.9.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.9.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.9.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.10.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.10.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.10.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.10.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.11.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.11.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.11.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.11.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.12.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.12.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.12.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.12.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model-00003-of-00006.bin'\n",
+ "INFO:hf-to-gguf:blk.13.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.13.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.13.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.13.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.14.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.14.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.14.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.14.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.15.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.15.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.15.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.15.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.16.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.16.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.16.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.16.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.17.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.17.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.17.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.17.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.18.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.18.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.18.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.18.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.19.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.19.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.19.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.19.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.20.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.20.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.20.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.20.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model-00004-of-00006.bin'\n",
+ "INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.21.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.21.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.21.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.21.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.22.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.22.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.22.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.22.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.23.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.23.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.23.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.23.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.24.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.24.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.24.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.24.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.24.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.24.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.24.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.24.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.25.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.25.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.25.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.25.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.25.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.25.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.25.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.25.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.26.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.26.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.26.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.26.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.26.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.26.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.26.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.26.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.27.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.27.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.27.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.27.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.27.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model-00005-of-00006.bin'\n",
+ "INFO:hf-to-gguf:blk.27.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.27.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.27.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.28.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.28.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.28.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.28.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.28.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.28.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.28.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.28.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.28.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.29.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.29.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.29.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.29.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.29.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.29.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.29.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.29.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.29.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.30.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.30.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.30.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.30.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.30.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.30.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.30.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.30.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.30.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.31.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.31.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.31.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.31.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.31.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.31.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.31.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.31.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.31.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.32.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.32.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.32.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.32.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.32.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.32.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.32.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.32.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.32.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.33.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.33.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.33.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.33.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.33.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.33.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.33.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.33.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.33.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.34.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.34.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.34.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.34.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.34.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.34.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model-00006-of-00006.bin'\n",
+ "INFO:hf-to-gguf:blk.34.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.34.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.34.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.35.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.35.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.35.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.35.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.35.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.35.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.35.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.35.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.35.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.36.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.36.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.36.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.36.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.36.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.36.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.36.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.36.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.36.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.37.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.37.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.37.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.37.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.37.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.37.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.37.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.37.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.37.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.38.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.38.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.38.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.38.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.38.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.38.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.38.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.38.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.38.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.39.attn_q.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.39.attn_k.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.39.attn_v.weight, torch.float16 --> Q8_0, shape = {5120, 1280}\n",
+ "INFO:hf-to-gguf:blk.39.attn_output.weight, torch.float16 --> Q8_0, shape = {5120, 5120}\n",
+ "INFO:hf-to-gguf:blk.39.ffn_gate.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.39.ffn_up.weight, torch.float16 --> Q8_0, shape = {5120, 17920}\n",
+ "INFO:hf-to-gguf:blk.39.ffn_down.weight, torch.float16 --> Q8_0, shape = {17920, 5120}\n",
+ "INFO:hf-to-gguf:blk.39.attn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:blk.39.ffn_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:output_norm.weight, torch.float16 --> F32, shape = {5120}\n",
+ "INFO:hf-to-gguf:output.weight, torch.float16 --> Q8_0, shape = {5120, 100352}\n",
+ "INFO:hf-to-gguf:Set meta model\n",
+ "INFO:hf-to-gguf:Set model parameters\n",
+ "INFO:hf-to-gguf:gguf: context length = 16384\n",
+ "INFO:hf-to-gguf:gguf: embedding length = 5120\n",
+ "INFO:hf-to-gguf:gguf: feed forward length = 17920\n",
+ "INFO:hf-to-gguf:gguf: head count = 40\n",
+ "INFO:hf-to-gguf:gguf: key-value head count = 10\n",
+ "INFO:hf-to-gguf:gguf: rope theta = 250000\n",
+ "INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05\n",
+ "INFO:hf-to-gguf:gguf: file type = 7\n",
+ "INFO:hf-to-gguf:Set model tokenizer\n",
+ "INFO:numexpr.utils:NumExpr defaulting to 2 threads.\n",
+ "2025-02-17 09:42:25.460750: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+ "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
+ "E0000 00:00:1739785345.797846 25019 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+ "E0000 00:00:1739785345.892835 25019 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+ "INFO:hf-to-gguf:'Γ―ΒΏΒ½' is encoded and decoded back to 'οΏ½' using AutoTokenizer\n",
+ "INFO:gguf.vocab:Adding 100000 merge(s).\n",
+ "INFO:gguf.vocab:Setting special token type bos to 100257\n",
+ "INFO:gguf.vocab:Setting special token type eos to 100265\n",
+ "INFO:gguf.vocab:Setting special token type unk to 5809\n",
+ "INFO:gguf.vocab:Setting special token type pad to 100351\n",
+ "INFO:gguf.vocab:Setting chat_template to {% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}\n",
+ "INFO:hf-to-gguf:Set model quantization version\n",
+ "INFO:gguf.gguf_writer:Writing the following files:\n",
+ "INFO:gguf.gguf_writer:/content/persadian_14B-GRPO/unsloth.Q8_0.gguf: n_tensors = 363, total_size = 15.6G\n",
+ "Writing: 100%|ββββββββββ| 15.6G/15.6G [16:52<00:00, 15.4Mbyte/s]\n",
+ "INFO:hf-to-gguf:Model successfully exported to /content/persadian_14B-GRPO/unsloth.Q8_0.gguf\n",
+ "Unsloth: Conversion completed! Output location: /content/persadian_14B-GRPO/unsloth.Q8_0.gguf\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Instead of:\n",
+ "# save_pretrained_gguf\n",
+ "\n",
+ "# Use:\n",
+ "model.save_pretrained_gguf(\"persadian_14B-GRPO\", tokenizer)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "qbQ156uZvhRq",
+ "outputId": "285c1097-4e5a-435b-d78e-56d826a452fc"
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Requirement already satisfied: unsloth==2025.2.4 in /usr/local/lib/python3.11/dist-packages (2025.2.4)\n",
+ "Requirement already satisfied: vllm in /usr/local/lib/python3.11/dist-packages (0.7.2)\n",
+ "Requirement already satisfied: unsloth_zoo>=2025.2.1 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (2025.2.5)\n",
+ "Requirement already satisfied: torch>=2.4.0 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (2.5.1+cu124)\n",
+ "Requirement already satisfied: xformers>=0.0.27.post2 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.0.28.post3)\n",
+ "Requirement already satisfied: bitsandbytes in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.45.2)\n",
+ "Requirement already satisfied: triton>=3.0.0 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (3.1.0)\n",
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (24.2)\n",
+ "Requirement already satisfied: tyro in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.9.14)\n",
+ "Requirement already satisfied: transformers!=4.47.0,>=4.46.1 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (4.48.3)\n",
+ "Requirement already satisfied: datasets>=2.16.0 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (3.3.0)\n",
+ "Requirement already satisfied: sentencepiece>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.2.0)\n",
+ "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (4.67.1)\n",
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (5.9.5)\n",
+ "Requirement already satisfied: wheel>=0.42.0 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.45.1)\n",
+ "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (1.26.4)\n",
+ "Requirement already satisfied: accelerate>=0.34.1 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (1.3.0)\n",
+ "Requirement already satisfied: trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.15.0.dev0)\n",
+ "Requirement already satisfied: peft!=0.11.0,>=0.7.1 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.14.0)\n",
+ "Requirement already satisfied: protobuf<4.0.0 in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (3.20.3)\n",
+ "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.28.1)\n",
+ "Requirement already satisfied: hf_transfer in /usr/local/lib/python3.11/dist-packages (from unsloth==2025.2.4) (0.1.9)\n",
+ "Requirement already satisfied: requests>=2.26.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (2.32.3)\n",
+ "Requirement already satisfied: blake3 in /usr/local/lib/python3.11/dist-packages (from vllm) (1.0.4)\n",
+ "Requirement already satisfied: py-cpuinfo in /usr/local/lib/python3.11/dist-packages (from vllm) (9.0.0)\n",
+ "Requirement already satisfied: tokenizers>=0.19.1 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.21.0)\n",
+ "Requirement already satisfied: fastapi!=0.113.*,!=0.114.0,>=0.107.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.115.8)\n",
+ "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from vllm) (3.11.12)\n",
+ "Requirement already satisfied: openai>=1.52.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (1.61.1)\n",
+ "Requirement already satisfied: uvicorn[standard] in /usr/local/lib/python3.11/dist-packages (from vllm) (0.34.0)\n",
+ "Requirement already satisfied: pydantic>=2.9 in /usr/local/lib/python3.11/dist-packages (from vllm) (2.10.6)\n",
+ "Requirement already satisfied: prometheus_client>=0.18.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.21.1)\n",
+ "Requirement already satisfied: pillow in /usr/local/lib/python3.11/dist-packages (from vllm) (11.1.0)\n",
+ "Requirement already satisfied: prometheus-fastapi-instrumentator>=7.0.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (7.0.2)\n",
+ "Requirement already satisfied: tiktoken>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.9.0)\n",
+ "Requirement already satisfied: lm-format-enforcer<0.11,>=0.10.9 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.10.10)\n",
+ "Requirement already satisfied: outlines==0.1.11 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.1.11)\n",
+ "Requirement already satisfied: lark==1.2.2 in /usr/local/lib/python3.11/dist-packages (from vllm) (1.2.2)\n",
+ "Requirement already satisfied: xgrammar>=0.1.6 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.1.13)\n",
+ "Requirement already satisfied: typing_extensions>=4.10 in /usr/local/lib/python3.11/dist-packages (from vllm) (4.12.2)\n",
+ "Requirement already satisfied: filelock>=3.16.1 in /usr/local/lib/python3.11/dist-packages (from vllm) (3.17.0)\n",
+ "Requirement already satisfied: partial-json-parser in /usr/local/lib/python3.11/dist-packages (from vllm) (0.2.1.1.post5)\n",
+ "Requirement already satisfied: pyzmq in /usr/local/lib/python3.11/dist-packages (from vllm) (24.0.1)\n",
+ "Requirement already satisfied: msgspec in /usr/local/lib/python3.11/dist-packages (from vllm) (0.19.0)\n",
+ "Requirement already satisfied: gguf==0.10.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.10.0)\n",
+ "Requirement already satisfied: importlib_metadata in /usr/local/lib/python3.11/dist-packages (from vllm) (8.6.1)\n",
+ "Requirement already satisfied: mistral_common>=1.5.0 in /usr/local/lib/python3.11/dist-packages (from mistral_common[opencv]>=1.5.0->vllm) (1.5.3)\n",
+ "Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/dist-packages (from vllm) (6.0.2)\n",
+ "Requirement already satisfied: einops in /usr/local/lib/python3.11/dist-packages (from vllm) (0.8.1)\n",
+ "Requirement already satisfied: compressed-tensors==0.9.1 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.9.1)\n",
+ "Requirement already satisfied: depyf==0.18.0 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.18.0)\n",
+ "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.11/dist-packages (from vllm) (3.1.1)\n",
+ "Requirement already satisfied: ray>=2.9 in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (2.42.1)\n",
+ "Requirement already satisfied: nvidia-ml-py>=12.560.30 in /usr/local/lib/python3.11/dist-packages (from vllm) (12.570.86)\n",
+ "Requirement already satisfied: torchaudio==2.5.1 in /usr/local/lib/python3.11/dist-packages (from vllm) (2.5.1+cu124)\n",
+ "Requirement already satisfied: torchvision==0.20.1 in /usr/local/lib/python3.11/dist-packages (from vllm) (0.20.1+cu124)\n",
+ "Requirement already satisfied: astor in /usr/local/lib/python3.11/dist-packages (from depyf==0.18.0->vllm) (0.8.1)\n",
+ "Requirement already satisfied: dill in /usr/local/lib/python3.11/dist-packages (from depyf==0.18.0->vllm) (0.3.8)\n",
+ "Requirement already satisfied: interegular in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (0.3.3)\n",
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (3.1.5)\n",
+ "Requirement already satisfied: nest_asyncio in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (1.6.0)\n",
+ "Requirement already satisfied: diskcache in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (5.6.3)\n",
+ "Requirement already satisfied: referencing in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (0.36.2)\n",
+ "Requirement already satisfied: jsonschema in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (4.23.0)\n",
+ "Requirement already satisfied: pycountry in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (24.6.1)\n",
+ "Requirement already satisfied: airportsdata in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (20241001)\n",
+ "Requirement already satisfied: outlines_core==0.1.26 in /usr/local/lib/python3.11/dist-packages (from outlines==0.1.11->vllm) (0.1.26)\n",
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (3.4.2)\n",
+ "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (2024.10.0)\n",
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (9.1.0.70)\n",
+ "Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.4.5.8)\n",
+ "Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (11.2.1.3)\n",
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (10.3.5.147)\n",
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (11.6.1.9)\n",
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.3.1.170)\n",
+ "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (2.21.5)\n",
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (12.4.127)\n",
+ "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch>=2.4.0->unsloth==2025.2.4) (1.13.1)\n",
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch>=2.4.0->unsloth==2025.2.4) (1.3.0)\n",
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.1->unsloth==2025.2.4) (0.5.2)\n",
+ "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->unsloth==2025.2.4) (17.0.0)\n",
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->unsloth==2025.2.4) (2.2.2)\n",
+ "Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->unsloth==2025.2.4) (3.5.0)\n",
+ "Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->unsloth==2025.2.4) (0.70.16)\n",
+ "Requirement already satisfied: starlette<0.46.0,>=0.40.0 in /usr/local/lib/python3.11/dist-packages (from fastapi!=0.113.*,!=0.114.0,>=0.107.0->vllm) (0.45.3)\n",
+ "Requirement already satisfied: opencv-python-headless>=4.0.0 in /usr/local/lib/python3.11/dist-packages (from mistral_common[opencv]>=1.5.0->vllm) (4.11.0.86)\n",
+ "Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.11/dist-packages (from openai>=1.52.0->vllm) (3.7.1)\n",
+ "Requirement already satisfied: distro<2,>=1.7.0 in /usr/local/lib/python3.11/dist-packages (from openai>=1.52.0->vllm) (1.9.0)\n",
+ "Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.11/dist-packages (from openai>=1.52.0->vllm) (0.28.1)\n",
+ "Requirement already satisfied: jiter<1,>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from openai>=1.52.0->vllm) (0.8.2)\n",
+ "Requirement already satisfied: sniffio in /usr/local/lib/python3.11/dist-packages (from openai>=1.52.0->vllm) (1.3.1)\n",
+ "Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.9->vllm) (0.7.0)\n",
+ "Requirement already satisfied: pydantic-core==2.27.2 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.9->vllm) (2.27.2)\n",
+ "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.11/dist-packages (from ray>=2.9->ray[default]>=2.9->vllm) (8.1.8)\n",
+ "Requirement already satisfied: msgpack<2.0.0,>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from ray>=2.9->ray[default]>=2.9->vllm) (1.1.0)\n",
+ "Requirement already satisfied: aiosignal in /usr/local/lib/python3.11/dist-packages (from ray>=2.9->ray[default]>=2.9->vllm) (1.3.2)\n",
+ "Requirement already satisfied: frozenlist in /usr/local/lib/python3.11/dist-packages (from ray>=2.9->ray[default]>=2.9->vllm) (1.5.0)\n",
+ "Requirement already satisfied: aiohttp-cors in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (0.7.0)\n",
+ "Requirement already satisfied: colorful in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (0.5.6)\n",
+ "Requirement already satisfied: opencensus in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (0.11.4)\n",
+ "Requirement already satisfied: smart-open in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (7.1.0)\n",
+ "Requirement already satisfied: virtualenv!=20.21.1,>=20.0.24 in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (20.29.2)\n",
+ "Requirement already satisfied: py-spy>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (0.4.0)\n",
+ "Requirement already satisfied: grpcio>=1.42.0 in /usr/local/lib/python3.11/dist-packages (from ray[default]>=2.9->vllm) (1.70.0)\n",
+ "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->vllm) (2.4.6)\n",
+ "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->vllm) (25.1.0)\n",
+ "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->vllm) (6.1.0)\n",
+ "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->vllm) (0.2.1)\n",
+ "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->vllm) (1.18.3)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.26.0->vllm) (3.4.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.26.0->vllm) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.26.0->vllm) (2.3.0)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.26.0->vllm) (2025.1.31)\n",
+ "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.11/dist-packages (from tiktoken>=0.6.0->vllm) (2024.11.6)\n",
+ "Requirement already satisfied: rich in /usr/local/lib/python3.11/dist-packages (from trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4) (13.9.4)\n",
+ "Requirement already satisfied: cut_cross_entropy in /usr/local/lib/python3.11/dist-packages (from unsloth_zoo>=2025.2.1->unsloth==2025.2.4) (25.1.1)\n",
+ "Requirement already satisfied: pybind11 in /usr/local/lib/python3.11/dist-packages (from xgrammar>=0.1.6->vllm) (2.13.6)\n",
+ "Requirement already satisfied: pytest in /usr/local/lib/python3.11/dist-packages (from xgrammar>=0.1.6->vllm) (8.3.4)\n",
+ "Requirement already satisfied: zipp>=3.20 in /usr/local/lib/python3.11/dist-packages (from importlib_metadata->vllm) (3.21.0)\n",
+ "Requirement already satisfied: docstring-parser>=0.15 in /usr/local/lib/python3.11/dist-packages (from tyro->unsloth==2025.2.4) (0.16)\n",
+ "Requirement already satisfied: shtab>=1.5.6 in /usr/local/lib/python3.11/dist-packages (from tyro->unsloth==2025.2.4) (1.7.1)\n",
+ "Requirement already satisfied: typeguard>=4.0.0 in /usr/local/lib/python3.11/dist-packages (from tyro->unsloth==2025.2.4) (4.4.1)\n",
+ "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.11/dist-packages (from uvicorn[standard]->vllm) (0.14.0)\n",
+ "Requirement already satisfied: httptools>=0.6.3 in /usr/local/lib/python3.11/dist-packages (from uvicorn[standard]->vllm) (0.6.4)\n",
+ "Requirement already satisfied: python-dotenv>=0.13 in /usr/local/lib/python3.11/dist-packages (from uvicorn[standard]->vllm) (1.0.1)\n",
+ "Requirement already satisfied: uvloop!=0.15.0,!=0.15.1,>=0.14.0 in /usr/local/lib/python3.11/dist-packages (from uvicorn[standard]->vllm) (0.21.0)\n",
+ "Requirement already satisfied: watchfiles>=0.13 in /usr/local/lib/python3.11/dist-packages (from uvicorn[standard]->vllm) (1.0.4)\n",
+ "Requirement already satisfied: websockets>=10.4 in /usr/local/lib/python3.11/dist-packages (from uvicorn[standard]->vllm) (14.2)\n",
+ "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx<1,>=0.23.0->openai>=1.52.0->vllm) (1.0.7)\n",
+ "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.11/dist-packages (from jsonschema->outlines==0.1.11->vllm) (2024.10.1)\n",
+ "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.11/dist-packages (from jsonschema->outlines==0.1.11->vllm) (0.22.3)\n",
+ "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich->trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4) (3.0.0)\n",
+ "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich->trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4) (2.18.0)\n",
+ "Requirement already satisfied: distlib<1,>=0.3.7 in /usr/local/lib/python3.11/dist-packages (from virtualenv!=20.21.1,>=20.0.24->ray[default]>=2.9->vllm) (0.3.9)\n",
+ "Requirement already satisfied: platformdirs<5,>=3.9.1 in /usr/local/lib/python3.11/dist-packages (from virtualenv!=20.21.1,>=20.0.24->ray[default]>=2.9->vllm) (4.3.6)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->outlines==0.1.11->vllm) (3.0.2)\n",
+ "Requirement already satisfied: opencensus-context>=0.1.3 in /usr/local/lib/python3.11/dist-packages (from opencensus->ray[default]>=2.9->vllm) (0.1.3)\n",
+ "Requirement already satisfied: six~=1.16 in /usr/local/lib/python3.11/dist-packages (from opencensus->ray[default]>=2.9->vllm) (1.17.0)\n",
+ "Requirement already satisfied: google-api-core<3.0.0,>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from opencensus->ray[default]>=2.9->vllm) (2.19.2)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.16.0->unsloth==2025.2.4) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.16.0->unsloth==2025.2.4) (2025.1)\n",
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.16.0->unsloth==2025.2.4) (2025.1)\n",
+ "Requirement already satisfied: iniconfig in /usr/local/lib/python3.11/dist-packages (from pytest->xgrammar>=0.1.6->vllm) (2.0.0)\n",
+ "Requirement already satisfied: pluggy<2,>=1.5 in /usr/local/lib/python3.11/dist-packages (from pytest->xgrammar>=0.1.6->vllm) (1.5.0)\n",
+ "Requirement already satisfied: wrapt in /usr/local/lib/python3.11/dist-packages (from smart-open->ray[default]>=2.9->vllm) (1.17.2)\n",
+ "Requirement already satisfied: googleapis-common-protos<2.0.dev0,>=1.56.2 in /usr/local/lib/python3.11/dist-packages (from google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (1.66.0)\n",
+ "Requirement already satisfied: proto-plus<2.0.0dev,>=1.22.3 in /usr/local/lib/python3.11/dist-packages (from google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (1.26.0)\n",
+ "Requirement already satisfied: google-auth<3.0.dev0,>=2.14.1 in /usr/local/lib/python3.11/dist-packages (from google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (2.27.0)\n",
+ "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich->trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4) (0.1.2)\n",
+ "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from google-auth<3.0.dev0,>=2.14.1->google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (5.5.1)\n",
+ "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.11/dist-packages (from google-auth<3.0.dev0,>=2.14.1->google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (0.4.1)\n",
+ "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.11/dist-packages (from google-auth<3.0.dev0,>=2.14.1->google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (4.9)\n",
+ "Requirement already satisfied: pyasn1<0.7.0,>=0.4.6 in /usr/local/lib/python3.11/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3.0.dev0,>=2.14.1->google-api-core<3.0.0,>=1.0.0->opencensus->ray[default]>=2.9->vllm) (0.6.1)\n",
+ "Requirement already satisfied: pillow in /usr/local/lib/python3.11/dist-packages (11.1.0)\n",
+ "Collecting git+https://github.com/huggingface/trl.git@e95f9fb74a3c3647b86f251b7e230ec51c64b72b\n",
+ " Cloning https://github.com/huggingface/trl.git (to revision e95f9fb74a3c3647b86f251b7e230ec51c64b72b) to /tmp/pip-req-build-9l4vzudc\n",
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/trl.git /tmp/pip-req-build-9l4vzudc\n",
+ " Running command git rev-parse -q --verify 'sha^e95f9fb74a3c3647b86f251b7e230ec51c64b72b'\n",
+ " Running command git fetch -q https://github.com/huggingface/trl.git e95f9fb74a3c3647b86f251b7e230ec51c64b72b\n",
+ " Running command git checkout -q e95f9fb74a3c3647b86f251b7e230ec51c64b72b\n",
+ " Resolved https://github.com/huggingface/trl.git to commit e95f9fb74a3c3647b86f251b7e230ec51c64b72b\n",
+ " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
+ " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
+ " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+ "Requirement already satisfied: accelerate>=0.34.0 in /usr/local/lib/python3.11/dist-packages (from trl==0.15.0.dev0) (1.3.0)\n",
+ "Requirement already satisfied: datasets>=2.21.0 in /usr/local/lib/python3.11/dist-packages (from trl==0.15.0.dev0) (3.3.0)\n",
+ "Requirement already satisfied: rich in /usr/local/lib/python3.11/dist-packages (from trl==0.15.0.dev0) (13.9.4)\n",
+ "Requirement already satisfied: transformers>=4.46.0 in /usr/local/lib/python3.11/dist-packages (from trl==0.15.0.dev0) (4.48.3)\n",
+ "Requirement already satisfied: numpy<3.0.0,>=1.17 in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (1.26.4)\n",
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (24.2)\n",
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (5.9.5)\n",
+ "Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (6.0.2)\n",
+ "Requirement already satisfied: torch>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (2.5.1+cu124)\n",
+ "Requirement already satisfied: huggingface-hub>=0.21.0 in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (0.28.1)\n",
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from accelerate>=0.34.0->trl==0.15.0.dev0) (0.5.2)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (3.17.0)\n",
+ "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (17.0.0)\n",
+ "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (0.3.8)\n",
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (2.2.2)\n",
+ "Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (2.32.3)\n",
+ "Requirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (4.67.1)\n",
+ "Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (3.5.0)\n",
+ "Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (0.70.16)\n",
+ "Requirement already satisfied: fsspec<=2024.12.0,>=2023.1.0 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets>=2.21.0->trl==0.15.0.dev0) (2024.10.0)\n",
+ "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from datasets>=2.21.0->trl==0.15.0.dev0) (3.11.12)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers>=4.46.0->trl==0.15.0.dev0) (2024.11.6)\n",
+ "Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers>=4.46.0->trl==0.15.0.dev0) (0.21.0)\n",
+ "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich->trl==0.15.0.dev0) (3.0.0)\n",
+ "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich->trl==0.15.0.dev0) (2.18.0)\n",
+ "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (2.4.6)\n",
+ "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (1.3.2)\n",
+ "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (25.1.0)\n",
+ "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (1.5.0)\n",
+ "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (6.1.0)\n",
+ "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (0.2.1)\n",
+ "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.21.0->trl==0.15.0.dev0) (1.18.3)\n",
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.21.0->accelerate>=0.34.0->trl==0.15.0.dev0) (4.12.2)\n",
+ "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich->trl==0.15.0.dev0) (0.1.2)\n",
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets>=2.21.0->trl==0.15.0.dev0) (3.4.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets>=2.21.0->trl==0.15.0.dev0) (3.10)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets>=2.21.0->trl==0.15.0.dev0) (2.3.0)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets>=2.21.0->trl==0.15.0.dev0) (2025.1.31)\n",
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (3.4.2)\n",
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (3.1.5)\n",
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (9.1.0.70)\n",
+ "Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.4.5.8)\n",
+ "Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (11.2.1.3)\n",
+ "Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (10.3.5.147)\n",
+ "Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (11.6.1.9)\n",
+ "Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.3.1.170)\n",
+ "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (2.21.5)\n",
+ "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.4.127)\n",
+ "Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (12.4.127)\n",
+ "Requirement already satisfied: triton==3.1.0 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (3.1.0)\n",
+ "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (1.13.1)\n",
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (1.3.0)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.21.0->trl==0.15.0.dev0) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.21.0->trl==0.15.0.dev0) (2025.1)\n",
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.21.0->trl==0.15.0.dev0) (2025.1)\n",
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas->datasets>=2.21.0->trl==0.15.0.dev0) (1.17.0)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=2.0.0->accelerate>=0.34.0->trl==0.15.0.dev0) (3.0.2)\n"
+ ]
+ }
+ ],
+ "source": [
+ "!pip install \"unsloth==2025.2.4\" vllm # Re-add this line to install the 'unsloth' package\n",
+ "!pip install --upgrade pillow # This also installs dependencies\n",
+ "!pip install git+https://github.com/huggingface/trl.git@e95f9fb74a3c3647b86f251b7e230ec51c64b72b # trl is a dependency of unsloth"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "trM2re-DvSFA"
+ },
+ "outputs": [],
+ "source": [
+ "from unsloth import FastLanguageModel, PatchFastRL\n",
+ "PatchFastRL(\"GRPO\", FastLanguageModel) # Remove the extra indentation\n",
+ "# ... (Other code for loading and initializing model) ..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!apt-get install cmake"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "xKq2z_grf_Sc",
+ "outputId": "6af5d534-e256-4a32-fbbc-5855e0e4b3f6"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "E: Could not open lock file /var/lib/dpkg/lock-frontend - open (28: No space left on device)\n",
+ "E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), are you root?\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!apt-get install build-essential"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "C2ycCUKagCXk",
+ "outputId": "49e76ef4-f854-42a7-bb60-1d47fc31e9bd"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "E: Could not open lock file /var/lib/dpkg/lock-frontend - open (28: No space left on device)\n",
+ "E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), are you root?\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!apt-get install git-lfs"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "fmV2j2cSgFAN",
+ "outputId": "4c073e98-d5ba-4c9b-f9bb-09f2d1b25ccb"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "E: Could not open lock file /var/lib/dpkg/lock-frontend - open (28: No space left on device)\n",
+ "E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), are you root?\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Assign a value to the 'command' variable before using it.\n",
+ "# For example:\n",
+ "command = \"apt-get install cmake build-essential git-lfs\"\n",
+ "print(f'Running command: {command}')"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "elXTvC5NgJpk",
+ "outputId": "4685a760-6ad3-41d3-e081-69b1f2bedc27"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Running command: apt-get install cmake build-essential git-lfs\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!apt-get install cmake build-essential git-lfs"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "PJ3W8NTGgNPs",
+ "outputId": "8de9976b-b365-4fa0-a8ca-080b7994d524"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "E: Could not open lock file /var/lib/dpkg/lock-frontend - open (28: No space left on device)\n",
+ "E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), are you root?\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!apt-get update # Update package lists\n",
+ "!apt-get install -y cmake build-essential git-lfs # Install necessary dependencies\n",
+ "!pip install ninja # Install ninja build system if needed"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "-gDKXsdlgitD",
+ "outputId": "7273b74a-9d08-43a3-a821-e17b046657b3"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Reading package lists... Error!\n",
+ "W: chown to _apt:root of directory /var/lib/apt/lists/partial failed - SetupAPTPartialDirectory (28: No space left on device)\n",
+ "W: chmod 0700 of directory /var/lib/apt/lists/partial failed - SetupAPTPartialDirectory (28: No space left on device)\n",
+ "W: chown to _apt:root of directory /var/lib/apt/lists/auxfiles failed - SetupAPTPartialDirectory (28: No space left on device)\n",
+ "W: chmod 0755 of directory /var/lib/apt/lists/auxfiles failed - SetupAPTPartialDirectory (28: No space left on device)\n",
+ "E: Could not open lock file /var/lib/apt/lists/lock - open (28: No space left on device)\n",
+ "E: Unable to lock directory /var/lib/apt/lists/\n",
+ "E: Write error - write (28: No space left on device)\n",
+ "E: Write error - write (28: No space left on device)\n",
+ "E: The package lists or status file could not be parsed or opened.\n",
+ "E: Could not open lock file /var/lib/dpkg/lock-frontend - open (28: No space left on device)\n",
+ "E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), are you root?\n",
+ "--- Logging error ---\n",
+ "Traceback (most recent call last):\n",
+ " File \"/usr/lib/python3.11/logging/__init__.py\", line 1114, in emit\n",
+ " self.flush()\n",
+ " File \"/usr/lib/python3.11/logging/__init__.py\", line 1094, in flush\n",
+ " self.stream.flush()\n",
+ "OSError: [Errno 28] No space left on device\n",
+ "Call stack:\n",
+ " File \"/usr/local/bin/pip3\", line 10, in \n",
+ " sys.exit(main())\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/main.py\", line 80, in main\n",
+ " return command.main(cmd_args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 100, in main\n",
+ " return self._main(args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 232, in _main\n",
+ " return run(options, args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 179, in exc_logging_wrapper\n",
+ " status = run_func(*args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/req_command.py\", line 67, in wrapper\n",
+ " return func(self, options, args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/commands/install.py\", line 293, in run\n",
+ " logger.verbose(\"Using %s\", get_pip_version())\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/utils/_log.py\", line 23, in verbose\n",
+ " return self.log(VERBOSE, msg, *args, **kwargs)\n",
+ "Message: 'Using %s'\n",
+ "Arguments: ('pip 24.1.2 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11)',)\n",
+ "--- Logging error ---\n",
+ "Traceback (most recent call last):\n",
+ " File \"/usr/lib/python3.11/logging/__init__.py\", line 1114, in emit\n",
+ " self.flush()\n",
+ " File \"/usr/lib/python3.11/logging/__init__.py\", line 1094, in flush\n",
+ " self.stream.flush()\n",
+ "OSError: [Errno 28] No space left on device\n",
+ "Call stack:\n",
+ " File \"/usr/local/bin/pip3\", line 10, in \n",
+ " sys.exit(main())\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/main.py\", line 80, in main\n",
+ " return command.main(cmd_args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 100, in main\n",
+ " return self._main(args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 232, in _main\n",
+ " return run(options, args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 179, in exc_logging_wrapper\n",
+ " status = run_func(*args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/req_command.py\", line 67, in wrapper\n",
+ " return func(self, options, args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/commands/install.py\", line 294, in run\n",
+ " options.use_user_site = decide_user_install(\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/commands/install.py\", line 713, in decide_user_install\n",
+ " logger.debug(\"Non-user install because site-packages writeable\")\n",
+ "Message: 'Non-user install because site-packages writeable'\n",
+ "Arguments: ()\n",
+ "\u001b[31mERROR: Exception:\n",
+ "Traceback (most recent call last):\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 179, in exc_logging_wrapper\n",
+ " status = run_func(*args)\n",
+ " ^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/req_command.py\", line 67, in wrapper\n",
+ " return func(self, options, args)\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/commands/install.py\", line 333, in run\n",
+ " build_tracker = self.enter_context(get_build_tracker())\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/command_context.py\", line 27, in enter_context\n",
+ " return self._main_context.enter_context(context_provider)\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/contextlib.py\", line 517, in enter_context\n",
+ " result = _enter(cm)\n",
+ " ^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/contextlib.py\", line 137, in __enter__\n",
+ " return next(self.gen)\n",
+ " ^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/operations/build/build_tracker.py\", line 45, in get_build_tracker\n",
+ " root = ctx.enter_context(TempDirectory(kind=\"build-tracker\")).path\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/utils/temp_dir.py\", line 137, in __init__\n",
+ " path = self._create(kind)\n",
+ " ^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/utils/temp_dir.py\", line 177, in _create\n",
+ " path = os.path.realpath(tempfile.mkdtemp(prefix=f\"pip-{kind}-\"))\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 513, in mkdtemp\n",
+ " prefix, suffix, dir, output_type = _sanitize_params(prefix, suffix, dir)\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 266, in _sanitize_params\n",
+ " dir = gettempdir()\n",
+ " ^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 455, in gettempdir\n",
+ " return _os.fsdecode(_gettempdir())\n",
+ " ^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 448, in _gettempdir\n",
+ " tempdir = _get_default_tempdir()\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 363, in _get_default_tempdir\n",
+ " raise FileNotFoundError(_errno.ENOENT,\n",
+ "FileNotFoundError: [Errno 2] No usable temporary directory found in ['/tmp', '/var/tmp', '/usr/tmp', '/content']\u001b[0m\u001b[31m\n",
+ "\u001b[0m--- Logging error ---\n",
+ "Traceback (most recent call last):\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 179, in exc_logging_wrapper\n",
+ " status = run_func(*args)\n",
+ " ^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/req_command.py\", line 67, in wrapper\n",
+ " return func(self, options, args)\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/commands/install.py\", line 333, in run\n",
+ " build_tracker = self.enter_context(get_build_tracker())\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/command_context.py\", line 27, in enter_context\n",
+ " return self._main_context.enter_context(context_provider)\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/contextlib.py\", line 517, in enter_context\n",
+ " result = _enter(cm)\n",
+ " ^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/contextlib.py\", line 137, in __enter__\n",
+ " return next(self.gen)\n",
+ " ^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/operations/build/build_tracker.py\", line 45, in get_build_tracker\n",
+ " root = ctx.enter_context(TempDirectory(kind=\"build-tracker\")).path\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/utils/temp_dir.py\", line 137, in __init__\n",
+ " path = self._create(kind)\n",
+ " ^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/utils/temp_dir.py\", line 177, in _create\n",
+ " path = os.path.realpath(tempfile.mkdtemp(prefix=f\"pip-{kind}-\"))\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 513, in mkdtemp\n",
+ " prefix, suffix, dir, output_type = _sanitize_params(prefix, suffix, dir)\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 266, in _sanitize_params\n",
+ " dir = gettempdir()\n",
+ " ^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 455, in gettempdir\n",
+ " return _os.fsdecode(_gettempdir())\n",
+ " ^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 448, in _gettempdir\n",
+ " tempdir = _get_default_tempdir()\n",
+ " ^^^^^^^^^^^^^^^^^^^^^^\n",
+ " File \"/usr/lib/python3.11/tempfile.py\", line 363, in _get_default_tempdir\n",
+ " raise FileNotFoundError(_errno.ENOENT,\n",
+ "FileNotFoundError: [Errno 2] No usable temporary directory found in ['/tmp', '/var/tmp', '/usr/tmp', '/content']\n",
+ "\n",
+ "During handling of the above exception, another exception occurred:\n",
+ "\n",
+ "Traceback (most recent call last):\n",
+ " File \"/usr/lib/python3.11/logging/__init__.py\", line 1114, in emit\n",
+ " self.flush()\n",
+ " File \"/usr/lib/python3.11/logging/__init__.py\", line 1094, in flush\n",
+ " self.stream.flush()\n",
+ "OSError: [Errno 28] No space left on device\n",
+ "Call stack:\n",
+ " File \"/usr/local/bin/pip3\", line 10, in \n",
+ " sys.exit(main())\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/main.py\", line 80, in main\n",
+ " return command.main(cmd_args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 100, in main\n",
+ " return self._main(args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 232, in _main\n",
+ " return run(options, args)\n",
+ " File \"/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py\", line 220, in exc_logging_wrapper\n",
+ " logger.critical(\"Exception:\", exc_info=True)\n",
+ "Message: 'Exception:'\n",
+ "Arguments: ()\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!rm -rf /tmp/* # Remove temporary files\n",
+ "!apt-get clean # Remove downloaded package files\n",
+ "!apt-get autoremove --purge # Remove unused packages\n",
+ "!df -h # Check disk usage to identify large files/folders\n",
+ "# du -sh * | sort -rh # to find large directories (use with caution)\n",
+ "# rm -rf # Remove large files or folders (use with extreme caution)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "omv2BbYVg60b",
+ "outputId": "433a0baa-f232-4c4f-8b81-ccc6deac318f"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "rm: cannot remove '/tmp/colab_runtime.sock': Device or resource busy\n",
+ "Reading package lists... Error!\n",
+ "E: Write error - write (28: No space left on device)\n",
+ "E: Write error - write (28: No space left on device)\n",
+ "E: The package lists or status file could not be parsed or opened.\n",
+ "Filesystem Size Used Avail Use% Mounted on\n",
+ "overlay 113G 113G 76K 100% /\n",
+ "tmpfs 64M 0 64M 0% /dev\n",
+ "shm 5.7G 24K 5.7G 1% /dev/shm\n",
+ "/dev/root 2.0G 1.2G 820M 59% /usr/sbin/docker-init\n",
+ "/dev/sda1 119G 115G 4.3G 97% /opt/bin/.nvidia\n",
+ "tmpfs 6.4G 3.1M 6.4G 1% /var/colab\n",
+ "tmpfs 6.4G 0 6.4G 0% /proc/acpi\n",
+ "tmpfs 6.4G 0 6.4G 0% /proc/scsi\n",
+ "tmpfs 6.4G 0 6.4G 0% /sys/firmware\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Step 1: Clean temporary directory and package caches thoroughly.\n",
+ "!rm -rf /tmp/*\n",
+ "!apt-get clean\n",
+ "!apt-get autoremove --purge\n",
+ "!df -h # Recheck disk usage\n",
+ "\n",
+ "# Step 2: Check and potentially remove old llama.cpp installation\n",
+ "!rm -rf llama.cpp # Removes the old llama.cpp directory if it exists\n",
+ "\n",
+ "# Step 3: Install or reinstall dependencies\n",
+ "!apt-get update # Update package lists\n",
+ "!apt-get install -y cmake build-essential git-lfs # Install necessary dependencies\n",
+ "!pip install ninja # Install ninja build system if needed\n",
+ "\n",
+ "# Step 4: Force reinstall unsloth to update associated files\n",
+ "!pip install --force-reinstall \"unsloth==2025.2.4\"\n",
+ "\n",
+ "# Step 5: Set up the model using unsloth and save in the desired format\n",
+ "from unsloth import FastLanguageModel, PatchFastRL\n",
+ "PatchFastRL(\"GRPO\", FastLanguageModel)\n",
+ "model.save_pretrained_merged(\"persadian_14B-GRPO\", tokenizer) # try saving without quantization initially"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000
+ },
+ "id": "zUNz64ulhTga",
+ "outputId": "89d9ae88-a098-4d7f-b2ba-b0326c741f53"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "rm: cannot remove '/tmp/colab_runtime.sock': Device or resource busy\n",
+ "Reading package lists... Error!\n",
+ "E: Write error - write (28: No space left on device)\n",
+ "E: Write error - write (28: No space left on device)\n",
+ "E: The package lists or status file could not be parsed or opened.\n",
+ "Filesystem Size Used Avail Use% Mounted on\n",
+ "overlay 113G 113G 0 100% /\n",
+ "tmpfs 64M 0 64M 0% /dev\n",
+ "shm 5.7G 24K 5.7G 1% /dev/shm\n",
+ "/dev/root 2.0G 1.2G 820M 59% /usr/sbin/docker-init\n",
+ "/dev/sda1 119G 115G 4.3G 97% /opt/bin/.nvidia\n",
+ "tmpfs 6.4G 3.1M 6.4G 1% /var/colab\n",
+ "tmpfs 6.4G 0 6.4G 0% /proc/acpi\n",
+ "tmpfs 6.4G 0 6.4G 0% /proc/scsi\n",
+ "tmpfs 6.4G 0 6.4G 0% /sys/firmware\n",
+ "Get:1 https://cloud.r-project.org/bin/linux/ubuntu jammy-cran40/ InRelease [3,632 B]\n",
+ "Hit:2 http://archive.ubuntu.com/ubuntu jammy InRelease\n",
+ "Get:3 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 InRelease [1,581 B]\n",
+ "Get:4 http://archive.ubuntu.com/ubuntu jammy-updates InRelease [128 kB]\n",
+ "Get:5 http://security.ubuntu.com/ubuntu jammy-security InRelease [129 kB]\n",
+ "Get:6 https://r2u.stat.illinois.edu/ubuntu jammy InRelease [6,555 B]\n",
+ "Get:7 http://archive.ubuntu.com/ubuntu jammy-backports InRelease [127 kB]\n",
+ "Hit:8 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu jammy InRelease\n",
+ "Get:9 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64 Packages [1,315 kB]\n",
+ "Hit:10 https://ppa.launchpadcontent.net/graphics-drivers/ppa/ubuntu jammy InRelease\n",
+ "Get:11 https://r2u.stat.illinois.edu/ubuntu jammy/main amd64 Packages [2,656 kB]\n",
+ "Hit:12 https://ppa.launchpadcontent.net/ubuntugis/ppa/ubuntu jammy InRelease\n",
+ "Get:13 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 Packages [2,911 kB]\n",
+ "Get:14 http://archive.ubuntu.com/ubuntu jammy-updates/universe amd64 Packages [1,526 kB]\n",
+ "Get:15 https://r2u.stat.illinois.edu/ubuntu jammy/main all Packages [8,677 kB]\n",
+ "Fetched 17.5 MB in 2s (9,132 kB/s)\n",
+ "Reading package lists... Done\n",
+ "W: Skipping acquire of configured file 'main/source/Sources' as repository 'https://r2u.stat.illinois.edu/ubuntu jammy InRelease' does not seem to provide it (sources.list entry misspelt?)\n",
+ "Reading package lists... Done\n",
+ "Building dependency tree... Done\n",
+ "Reading state information... Done\n",
+ "build-essential is already the newest version (12.9ubuntu3).\n",
+ "cmake is already the newest version (3.22.1-1ubuntu1.22.04.2).\n",
+ "git-lfs is already the newest version (3.0.2-1ubuntu0.3).\n",
+ "0 upgraded, 0 newly installed, 0 to remove and 22 not upgraded.\n",
+ "Collecting ninja\n",
+ " Downloading ninja-1.11.1.3-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl.metadata (5.3 kB)\n",
+ "Downloading ninja-1.11.1.3-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (422 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m422.9/422.9 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hInstalling collected packages: ninja\n",
+ "Successfully installed ninja-1.11.1.3\n",
+ "Collecting unsloth==2025.2.4\n",
+ " Using cached unsloth-2025.2.4-py3-none-any.whl.metadata (57 kB)\n",
+ "Collecting unsloth_zoo>=2025.2.1 (from unsloth==2025.2.4)\n",
+ " Using cached unsloth_zoo-2025.2.5-py3-none-any.whl.metadata (16 kB)\n",
+ "Collecting torch>=2.4.0 (from unsloth==2025.2.4)\n",
+ " Downloading torch-2.6.0-cp311-cp311-manylinux1_x86_64.whl.metadata (28 kB)\n",
+ "Collecting xformers>=0.0.27.post2 (from unsloth==2025.2.4)\n",
+ " Using cached xformers-0.0.29.post3-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (1.0 kB)\n",
+ "Collecting bitsandbytes (from unsloth==2025.2.4)\n",
+ " Using cached bitsandbytes-0.45.2-py3-none-manylinux_2_24_x86_64.whl.metadata (5.8 kB)\n",
+ "Collecting triton>=3.0.0 (from unsloth==2025.2.4)\n",
+ " Downloading triton-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
+ "Collecting packaging (from unsloth==2025.2.4)\n",
+ " Downloading packaging-24.2-py3-none-any.whl.metadata (3.2 kB)\n",
+ "Collecting tyro (from unsloth==2025.2.4)\n",
+ " Using cached tyro-0.9.14-py3-none-any.whl.metadata (9.4 kB)\n",
+ "Collecting transformers!=4.47.0,>=4.46.1 (from unsloth==2025.2.4)\n",
+ " Downloading transformers-4.48.3-py3-none-any.whl.metadata (44 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m44.4/44.4 kB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting datasets>=2.16.0 (from unsloth==2025.2.4)\n",
+ " Using cached datasets-3.3.0-py3-none-any.whl.metadata (19 kB)\n",
+ "Collecting sentencepiece>=0.2.0 (from unsloth==2025.2.4)\n",
+ " Downloading sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)\n",
+ "Collecting tqdm (from unsloth==2025.2.4)\n",
+ " Downloading tqdm-4.67.1-py3-none-any.whl.metadata (57 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m57.7/57.7 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting psutil (from unsloth==2025.2.4)\n",
+ " Downloading psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (22 kB)\n",
+ "Collecting wheel>=0.42.0 (from unsloth==2025.2.4)\n",
+ " Downloading wheel-0.45.1-py3-none-any.whl.metadata (2.3 kB)\n",
+ "Collecting numpy (from unsloth==2025.2.4)\n",
+ " Downloading numpy-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (62 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m62.0/62.0 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting accelerate>=0.34.1 (from unsloth==2025.2.4)\n",
+ " Downloading accelerate-1.3.0-py3-none-any.whl.metadata (19 kB)\n",
+ "Collecting trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9 (from unsloth==2025.2.4)\n",
+ " Using cached trl-0.15.0-py3-none-any.whl.metadata (11 kB)\n",
+ "Collecting peft!=0.11.0,>=0.7.1 (from unsloth==2025.2.4)\n",
+ " Downloading peft-0.14.0-py3-none-any.whl.metadata (13 kB)\n",
+ "Collecting protobuf<4.0.0 (from unsloth==2025.2.4)\n",
+ " Using cached protobuf-3.20.3-py2.py3-none-any.whl.metadata (720 bytes)\n",
+ "Collecting huggingface_hub (from unsloth==2025.2.4)\n",
+ " Downloading huggingface_hub-0.28.1-py3-none-any.whl.metadata (13 kB)\n",
+ "Collecting hf_transfer (from unsloth==2025.2.4)\n",
+ " Using cached hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.7 kB)\n",
+ "Collecting pyyaml (from accelerate>=0.34.1->unsloth==2025.2.4)\n",
+ " Downloading PyYAML-6.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.1 kB)\n",
+ "Collecting safetensors>=0.4.3 (from accelerate>=0.34.1->unsloth==2025.2.4)\n",
+ " Downloading safetensors-0.5.2-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
+ "Collecting filelock (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading filelock-3.17.0-py3-none-any.whl.metadata (2.9 kB)\n",
+ "Collecting pyarrow>=15.0.0 (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading pyarrow-19.0.0-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (3.3 kB)\n",
+ "Collecting dill<0.3.9,>=0.3.0 (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Using cached dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
+ "Collecting pandas (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (89 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m89.9/89.9 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting requests>=2.32.2 (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading requests-2.32.3-py3-none-any.whl.metadata (4.6 kB)\n",
+ "Collecting xxhash (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Using cached xxhash-3.5.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
+ "Collecting multiprocess<0.70.17 (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Using cached multiprocess-0.70.16-py311-none-any.whl.metadata (7.2 kB)\n",
+ "Collecting fsspec<=2024.12.0,>=2023.1.0 (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)\n",
+ "Collecting aiohttp (from datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading aiohttp-3.11.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.7 kB)\n",
+ "Collecting typing-extensions>=3.7.4.3 (from huggingface_hub->unsloth==2025.2.4)\n",
+ " Downloading typing_extensions-4.12.2-py3-none-any.whl.metadata (3.0 kB)\n",
+ "Collecting networkx (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading networkx-3.4.2-py3-none-any.whl.metadata (6.3 kB)\n",
+ "Collecting jinja2 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading jinja2-3.1.5-py3-none-any.whl.metadata (2.6 kB)\n",
+ "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cublas-cu12==12.4.5.8 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cufft-cu12==11.2.1.3 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-curand-cu12==10.3.5.147 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
+ "Collecting nvidia-cusparselt-cu12==0.6.2 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl.metadata (6.8 kB)\n",
+ "Collecting nvidia-nccl-cu12==2.21.5 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n",
+ "Collecting nvidia-nvtx-cu12==12.4.127 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.7 kB)\n",
+ "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
+ "Collecting sympy==1.13.1 (from torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading sympy-1.13.1-py3-none-any.whl.metadata (12 kB)\n",
+ "Collecting mpmath<1.4,>=1.1.0 (from sympy==1.13.1->torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)\n",
+ "Collecting regex!=2019.12.17 (from transformers!=4.47.0,>=4.46.1->unsloth==2025.2.4)\n",
+ " Downloading regex-2024.11.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m40.5/40.5 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting tokenizers<0.22,>=0.21 (from transformers!=4.47.0,>=4.46.1->unsloth==2025.2.4)\n",
+ " Downloading tokenizers-0.21.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
+ "Collecting rich (from trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4)\n",
+ " Downloading rich-13.9.4-py3-none-any.whl.metadata (18 kB)\n",
+ "Collecting cut_cross_entropy (from unsloth_zoo>=2025.2.1->unsloth==2025.2.4)\n",
+ " Using cached cut_cross_entropy-25.1.1-py3-none-any.whl.metadata (9.3 kB)\n",
+ "Collecting pillow (from unsloth_zoo>=2025.2.1->unsloth==2025.2.4)\n",
+ " Downloading pillow-11.1.0-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (9.1 kB)\n",
+ "Collecting docstring-parser>=0.15 (from tyro->unsloth==2025.2.4)\n",
+ " Downloading docstring_parser-0.16-py3-none-any.whl.metadata (3.0 kB)\n",
+ "Collecting shtab>=1.5.6 (from tyro->unsloth==2025.2.4)\n",
+ " Using cached shtab-1.7.1-py3-none-any.whl.metadata (7.3 kB)\n",
+ "Collecting typeguard>=4.0.0 (from tyro->unsloth==2025.2.4)\n",
+ " Downloading typeguard-4.4.2-py3-none-any.whl.metadata (3.8 kB)\n",
+ "Collecting aiohappyeyeballs>=2.3.0 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading aiohappyeyeballs-2.4.6-py3-none-any.whl.metadata (5.9 kB)\n",
+ "Collecting aiosignal>=1.1.2 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading aiosignal-1.3.2-py2.py3-none-any.whl.metadata (3.8 kB)\n",
+ "Collecting attrs>=17.3.0 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading attrs-25.1.0-py3-none-any.whl.metadata (10 kB)\n",
+ "Collecting frozenlist>=1.1.1 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading frozenlist-1.5.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (13 kB)\n",
+ "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading multidict-6.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.0 kB)\n",
+ "Collecting propcache>=0.2.0 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading propcache-0.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (9.2 kB)\n",
+ "Collecting yarl<2.0,>=1.17.0 (from aiohttp->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading yarl-1.18.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (69 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m69.2/69.2 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting charset-normalizer<4,>=2 (from requests>=2.32.2->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (35 kB)\n",
+ "Collecting idna<4,>=2.5 (from requests>=2.32.2->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading idna-3.10-py3-none-any.whl.metadata (10 kB)\n",
+ "Collecting urllib3<3,>=1.21.1 (from requests>=2.32.2->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading urllib3-2.3.0-py3-none-any.whl.metadata (6.5 kB)\n",
+ "Collecting certifi>=2017.4.17 (from requests>=2.32.2->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading certifi-2025.1.31-py3-none-any.whl.metadata (2.5 kB)\n",
+ "Collecting markdown-it-py>=2.2.0 (from rich->trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4)\n",
+ " Downloading markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)\n",
+ "Collecting pygments<3.0.0,>=2.13.0 (from rich->trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4)\n",
+ " Downloading pygments-2.19.1-py3-none-any.whl.metadata (2.5 kB)\n",
+ "Collecting MarkupSafe>=2.0 (from jinja2->torch>=2.4.0->unsloth==2025.2.4)\n",
+ " Downloading MarkupSafe-3.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)\n",
+ "Collecting python-dateutil>=2.8.2 (from pandas->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading python_dateutil-2.9.0.post0-py2.py3-none-any.whl.metadata (8.4 kB)\n",
+ "Collecting pytz>=2020.1 (from pandas->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading pytz-2025.1-py2.py3-none-any.whl.metadata (22 kB)\n",
+ "Collecting tzdata>=2022.7 (from pandas->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading tzdata-2025.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
+ "Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich->trl!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,>=0.7.9->unsloth==2025.2.4)\n",
+ " Downloading mdurl-0.1.2-py3-none-any.whl.metadata (1.6 kB)\n",
+ "Collecting six>=1.5 (from python-dateutil>=2.8.2->pandas->datasets>=2.16.0->unsloth==2025.2.4)\n",
+ " Downloading six-1.17.0-py2.py3-none-any.whl.metadata (1.7 kB)\n",
+ "Using cached unsloth-2025.2.4-py3-none-any.whl (181 kB)\n",
+ "Downloading accelerate-1.3.0-py3-none-any.whl (336 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m336.6/336.6 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hUsing cached datasets-3.3.0-py3-none-any.whl (484 kB)\n",
+ "Downloading huggingface_hub-0.28.1-py3-none-any.whl (464 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m464.1/464.1 kB\u001b[0m \u001b[31m19.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading numpy-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.4 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m16.4/16.4 MB\u001b[0m \u001b[31m54.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading packaging-24.2-py3-none-any.whl (65 kB)\n",
+ "\u001b[2K \u001b[90mβββββββββββββββββββββββββββββββββοΏ½οΏ½ββββββ\u001b[0m \u001b[32m65.5/65.5 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading peft-0.14.0-py3-none-any.whl (374 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m374.8/374.8 kB\u001b[0m \u001b[31m31.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hUsing cached protobuf-3.20.3-py2.py3-none-any.whl (162 kB)\n",
+ "Downloading sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m67.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hDownloading torch-2.6.0-cp311-cp311-manylinux1_x86_64.whl (766.7 MB)\n",
+ "\u001b[2K \u001b[91mβββ\u001b[0m\u001b[90mβΊ\u001b[0m\u001b[90mββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m59.1/766.7 MB\u001b[0m \u001b[31m116.0 MB/s\u001b[0m eta \u001b[36m0:00:07\u001b[0m\n",
+ "\u001b[?25h\u001b[31mERROR: Could not install packages due to an OSError: [Errno 28] No space left on device\n",
+ "\u001b[0m\u001b[31m\n",
+ "\u001b[0mUnsloth: Merging 4bit and LoRA weights to 16bit...\n",
+ "Unsloth: Will use up to 3.0 out of 12.67 RAM for saving.\n",
+ "Unsloth: Saving model... This might take 5 minutes ...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ " 0%| | 0/40 [00:00, ?it/s]\n"
+ ]
+ },
+ {
+ "output_type": "error",
+ "ename": "RuntimeError",
+ "evalue": "[enforce fail at inline_container.cc:603] . unexpected pos 576 vs 470",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/serialization.py\u001b[0m in \u001b[0;36msave\u001b[0;34m(obj, f, pickle_module, pickle_protocol, _use_new_zipfile_serialization, _disable_byteorder_record)\u001b[0m\n\u001b[1;32m 849\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0m_open_zipfile_writer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mopened_zipfile\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 850\u001b[0;31m _save(\n\u001b[0m\u001b[1;32m 851\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/serialization.py\u001b[0m in \u001b[0;36m_save\u001b[0;34m(obj, zip_file, pickle_module, pickle_protocol, _disable_byteorder_record)\u001b[0m\n\u001b[1;32m 1113\u001b[0m \u001b[0;31m# Now that it is on the CPU we can directly copy it into the zip file\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1114\u001b[0;31m \u001b[0mzip_file\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite_record\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstorage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_bytes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1115\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mRuntimeError\u001b[0m: [enforce fail at inline_container.cc:778] . PytorchStreamWriter failed writing file data/0: file write failed",
+ "\nDuring handling of the above exception, another exception occurred:\n",
+ "\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0munsloth\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mFastLanguageModel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mPatchFastRL\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0mPatchFastRL\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"GRPO\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mFastLanguageModel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 21\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_pretrained_merged\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"persadian_14B-GRPO\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# try saving without quantization initially\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/unsloth/save.py\u001b[0m in \u001b[0;36munsloth_save_pretrained_merged\u001b[0;34m(self, save_directory, tokenizer, save_method, push_to_hub, token, is_main_process, state_dict, save_function, max_shard_size, safe_serialization, variant, save_peft_format, tags, temporary_location, maximum_memory_usage)\u001b[0m\n\u001b[1;32m 1296\u001b[0m \u001b[0marguments\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"model\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1297\u001b[0m \u001b[0;32mdel\u001b[0m \u001b[0marguments\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"self\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1298\u001b[0;31m \u001b[0munsloth_save_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0marguments\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1299\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0m_\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1300\u001b[0m \u001b[0mgc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcollect\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/utils/_contextlib.py\u001b[0m in \u001b[0;36mdecorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 114\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mdecorate_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 115\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mctx_factory\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 116\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 117\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 118\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mdecorate_context\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/unsloth/save.py\u001b[0m in \u001b[0;36munsloth_save_model\u001b[0;34m(model, tokenizer, save_directory, save_method, push_to_hub, token, is_main_process, state_dict, save_function, max_shard_size, safe_serialization, variant, save_peft_format, use_temp_dir, commit_message, private, create_pr, revision, commit_description, tags, temporary_location, maximum_memory_usage)\u001b[0m\n\u001b[1;32m 581\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwarning_once\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"\\nWe will save to Disk and not RAM now.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[0mfilename\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtemporary_location\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34mf\"{name}.pt\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 583\u001b[0;31m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mW\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpickle_module\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpickle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpickle_protocol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpickle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mHIGHEST_PROTOCOL\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 584\u001b[0m \u001b[0;31m# weights_only = True weirdly fails?\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 585\u001b[0m \u001b[0mstate_dict\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmap_location\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"cpu\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmmap\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mweights_only\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/serialization.py\u001b[0m in \u001b[0;36msave\u001b[0;34m(obj, f, pickle_module, pickle_protocol, _use_new_zipfile_serialization, _disable_byteorder_record)\u001b[0m\n\u001b[1;32m 847\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 848\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0m_use_new_zipfile_serialization\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 849\u001b[0;31m \u001b[0;32mwith\u001b[0m \u001b[0m_open_zipfile_writer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mopened_zipfile\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 850\u001b[0m _save(\n\u001b[1;32m 851\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m/usr/local/lib/python3.11/dist-packages/torch/serialization.py\u001b[0m in \u001b[0;36m__exit__\u001b[0;34m(self, *args)\u001b[0m\n\u001b[1;32m 688\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 689\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__exit__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 690\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfile_like\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite_end_of_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 691\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfile_stream\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 692\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfile_stream\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mRuntimeError\u001b[0m: [enforce fail at inline_container.cc:603] . unexpected pos 576 vs 470"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 176
+ },
+ "id": "o3fFOqAIh0rT",
+ "outputId": "1ecff26d-2478-4862-d9e6-2acbc0909d2c"
+ },
+ "outputs": [
+ {
+ "output_type": "error",
+ "ename": "NameError",
+ "evalue": "name 'model' is not defined",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m\u001b[0m in \u001b[0;36m| \u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Assuming 'model' is an instance of FastLanguageModel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;31m# And you have your Hugging Face token\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpush_to_hub_gguf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"hf/persadian_14B-GRPO\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtoken\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# Replace hf/model and YOUR_TOKEN\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m: name 'model' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "# Assuming 'model' is an instance of FastLanguageModel\n",
+ "# And you have your Hugging Face token\n",
+ "model.push_to_hub_gguf(\"darjyo/persadian_14B-GRPO\", tokenizer, token = \"\") # Replace hf/model and YOUR_TOKEN"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Mw7WBLmrr4Du"
+ },
+ "source": []
+ }
+ ],
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "gpuType": "T4",
+ "provenance": [],
+ "toc_visible": true
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "f6cdfd55751c4b25bba036f935ab3f07": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_6c7fd7892301407a8b2ec47c3de4147f",
+ "IPY_MODEL_be28b976f3454f1fac9cf7fa550d7025",
+ "IPY_MODEL_36e49fb358c649eba9385aabf40bd002"
+ ],
+ "layout": "IPY_MODEL_481ff3d0e7784013aa69552ba2cb112d"
+ }
+ },
+ "6c7fd7892301407a8b2ec47c3de4147f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_fe95bd8bdff445f985b9d2c5f41f8602",
+ "placeholder": "β",
+ "style": "IPY_MODEL_3c4608e1efcc4c26af345bcd76ae6314",
+ "value": "config.json:β100%"
+ }
+ },
+ "be28b976f3454f1fac9cf7fa550d7025": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_8015a02f160b4369b4382a13c0d155a2",
+ "max": 1397,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_3f19b40a2f294420b8ad741e33ceb7d4",
+ "value": 1397
+ }
+ },
+ "36e49fb358c649eba9385aabf40bd002": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b04e78369a8044e8b9a056f963461f4b",
+ "placeholder": "β",
+ "style": "IPY_MODEL_b96661e411eb474f809ca15789de914b",
+ "value": "β1.40k/1.40kβ[00:00<00:00,β104kB/s]"
+ }
+ },
+ "481ff3d0e7784013aa69552ba2cb112d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "fe95bd8bdff445f985b9d2c5f41f8602": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "3c4608e1efcc4c26af345bcd76ae6314": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "8015a02f160b4369b4382a13c0d155a2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "3f19b40a2f294420b8ad741e33ceb7d4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "b04e78369a8044e8b9a056f963461f4b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b96661e411eb474f809ca15789de914b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "4b50e8e72406478a93d86825e255e580": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_f13a7454f09244b990e8a801242f30c5",
+ "IPY_MODEL_c3714ffbb83f44f99236a7274d833528",
+ "IPY_MODEL_b622ce7659e840efb495bebf4f7d0c8d"
+ ],
+ "layout": "IPY_MODEL_dfd56e4bcf554e45a09a1b05aff1c1ab"
+ }
+ },
+ "f13a7454f09244b990e8a801242f30c5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_23c48ba794634d9ab72764008ec4ce62",
+ "placeholder": "β",
+ "style": "IPY_MODEL_e09e92afa3a54f8e986e816206dd5b08",
+ "value": "tokenizer_config.json:β100%"
+ }
+ },
+ "c3714ffbb83f44f99236a7274d833528": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d193009eb88e4cb7aae5337bdd35379e",
+ "max": 17989,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_6dde6c2c25f049c5b8d6dfdbd22bc752",
+ "value": 17989
+ }
+ },
+ "b622ce7659e840efb495bebf4f7d0c8d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_09b9a7b158c94a3bb32f4c292727e39f",
+ "placeholder": "β",
+ "style": "IPY_MODEL_c336adfe2a774a88abfb6177adebc4de",
+ "value": "β18.0k/18.0kβ[00:00<00:00,β850kB/s]"
+ }
+ },
+ "dfd56e4bcf554e45a09a1b05aff1c1ab": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "23c48ba794634d9ab72764008ec4ce62": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "e09e92afa3a54f8e986e816206dd5b08": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "d193009eb88e4cb7aae5337bdd35379e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "6dde6c2c25f049c5b8d6dfdbd22bc752": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "09b9a7b158c94a3bb32f4c292727e39f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c336adfe2a774a88abfb6177adebc4de": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "aac912a5d0b343ff8eee265f49acda2f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_8a6d772c4b6f4df3ac90ce7dc210c0af",
+ "IPY_MODEL_6ad9f2392c9a4d9b83e3818685e10f37",
+ "IPY_MODEL_4c2f698852304c989aa440a3ccb30079"
+ ],
+ "layout": "IPY_MODEL_3e4c00cdd5404a4f8f2a3e0978287ded"
+ }
+ },
+ "8a6d772c4b6f4df3ac90ce7dc210c0af": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c6eeda8dabdc4ed6879f21849f7acdcb",
+ "placeholder": "β",
+ "style": "IPY_MODEL_4ae91de48fa64f3589327abeb4c42fea",
+ "value": "vocab.json:β100%"
+ }
+ },
+ "6ad9f2392c9a4d9b83e3818685e10f37": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_7097460be2bc4243823f03d0d3c7b444",
+ "max": 1612637,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_9bc992eba8a74f669b28d7d952a73a90",
+ "value": 1612637
+ }
+ },
+ "4c2f698852304c989aa440a3ccb30079": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_a4643bd78a2b4d8d95e2e08b325df6c7",
+ "placeholder": "β",
+ "style": "IPY_MODEL_ff91b6b814f04d2599a8cb7c640f7c95",
+ "value": "β1.61M/1.61Mβ[00:00<00:00,β2.00MB/s]"
+ }
+ },
+ "3e4c00cdd5404a4f8f2a3e0978287ded": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c6eeda8dabdc4ed6879f21849f7acdcb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "4ae91de48fa64f3589327abeb4c42fea": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "7097460be2bc4243823f03d0d3c7b444": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9bc992eba8a74f669b28d7d952a73a90": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "a4643bd78a2b4d8d95e2e08b325df6c7": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ff91b6b814f04d2599a8cb7c640f7c95": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "15de40f79263474ca473b0494ac171a5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_f26d39fde70049349911f409a41debb9",
+ "IPY_MODEL_7d2eb02eda06476fbe165bd91d3ec0de",
+ "IPY_MODEL_f9dfc691492d45aaaf788ae227034b35"
+ ],
+ "layout": "IPY_MODEL_03c5239792d942fbb9077fa9a5b15e92"
+ }
+ },
+ "f26d39fde70049349911f409a41debb9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_e32ccfeea9a34d2ebae6b358be9a66ef",
+ "placeholder": "β",
+ "style": "IPY_MODEL_7ad16a66bbf741a789f6625d4fcc023f",
+ "value": "merges.txt:β100%"
+ }
+ },
+ "7d2eb02eda06476fbe165bd91d3ec0de": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_947bd19136174b758959833a0f969407",
+ "max": 916646,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_7884fc70984b4479abb473f14de99409",
+ "value": 916646
+ }
+ },
+ "f9dfc691492d45aaaf788ae227034b35": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b3058e3e8f90493793ae31ea7f42572a",
+ "placeholder": "β",
+ "style": "IPY_MODEL_102e6e7e53524fdeb3d4020ad6abcfe4",
+ "value": "β917k/917kβ[00:00<00:00,β1.90MB/s]"
+ }
+ },
+ "03c5239792d942fbb9077fa9a5b15e92": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "e32ccfeea9a34d2ebae6b358be9a66ef": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "7ad16a66bbf741a789f6625d4fcc023f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "947bd19136174b758959833a0f969407": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "7884fc70984b4479abb473f14de99409": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "b3058e3e8f90493793ae31ea7f42572a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "102e6e7e53524fdeb3d4020ad6abcfe4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "534f66ec60a2491db378b1239deb42ef": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_a4598817e02540feb95eca13aa3d1008",
+ "IPY_MODEL_c1b56a556e684b38a9c78d43d4edad28",
+ "IPY_MODEL_011cfb402b6143e9bf97bf83ab9422d9"
+ ],
+ "layout": "IPY_MODEL_09860d09e5ae489383ef6a099ed4bca3"
+ }
+ },
+ "a4598817e02540feb95eca13aa3d1008": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_65ae205166744508898dc82a16e7cc04",
+ "placeholder": "β",
+ "style": "IPY_MODEL_b3aa050d017d4a5a9bdd962f98736b24",
+ "value": "tokenizer.json:β100%"
+ }
+ },
+ "c1b56a556e684b38a9c78d43d4edad28": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c843aee0a4af4372876f1b66ae788617",
+ "max": 7153264,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_1ee3e07aaa684199b4c34b5b6469a60c",
+ "value": 7153264
+ }
+ },
+ "011cfb402b6143e9bf97bf83ab9422d9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c149b7f039fb45538e98222eaad21fc3",
+ "placeholder": "β",
+ "style": "IPY_MODEL_95315475337b45d699c4a56e6ff44136",
+ "value": "β7.15M/7.15Mβ[00:01<00:00,β7.27MB/s]"
+ }
+ },
+ "09860d09e5ae489383ef6a099ed4bca3": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "65ae205166744508898dc82a16e7cc04": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b3aa050d017d4a5a9bdd962f98736b24": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c843aee0a4af4372876f1b66ae788617": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1ee3e07aaa684199b4c34b5b6469a60c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "c149b7f039fb45538e98222eaad21fc3": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "95315475337b45d699c4a56e6ff44136": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "a72e220f7033480e8a59ad6a1b04337b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_db4a105befac44b69813fa2a641280b7",
+ "IPY_MODEL_f13745853f8f4f98b88179a13057cd5c",
+ "IPY_MODEL_b2ee0e317f0349b694502c395e0031a0"
+ ],
+ "layout": "IPY_MODEL_5141a74bb0d840e288c80cdad2fab75c"
+ }
+ },
+ "db4a105befac44b69813fa2a641280b7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_9241d465f6104fbb8c36be352265238f",
+ "placeholder": "β",
+ "style": "IPY_MODEL_53c007717fc043d4a64c9e9fa077fffd",
+ "value": "special_tokens_map.json:β100%"
+ }
+ },
+ "f13745853f8f4f98b88179a13057cd5c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_df3c5b477d2d4a03a3436c1becf61e0f",
+ "max": 570,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_46c726097cc840a5b61af5559cc1af4c",
+ "value": 570
+ }
+ },
+ "b2ee0e317f0349b694502c395e0031a0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_7fe26c30386f44d3a656132b6aded2fd",
+ "placeholder": "β",
+ "style": "IPY_MODEL_a1f928630ff54048afaf2f31783bfbd1",
+ "value": "β570/570β[00:00<00:00,β11.9kB/s]"
+ }
+ },
+ "5141a74bb0d840e288c80cdad2fab75c": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9241d465f6104fbb8c36be352265238f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "53c007717fc043d4a64c9e9fa077fffd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "df3c5b477d2d4a03a3436c1becf61e0f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "46c726097cc840a5b61af5559cc1af4c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "7fe26c30386f44d3a656132b6aded2fd": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "a1f928630ff54048afaf2f31783bfbd1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "f72c52ac4b4d48ae937585b0413b92b4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_99f8305417d046c1a14b6f6917b617fe",
+ "IPY_MODEL_45cdaabb1a25494da00671d8a61cca02",
+ "IPY_MODEL_bd1957ea932d4365b314044dbcc904f7"
+ ],
+ "layout": "IPY_MODEL_2eb96730c5ec4bc6abbc4e6fde479904"
+ }
+ },
+ "99f8305417d046c1a14b6f6917b617fe": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_112b11adf39344558b2dbc62b2f2c34e",
+ "placeholder": "β",
+ "style": "IPY_MODEL_268a421a0ce348c6a0221dabf2aab752",
+ "value": "generation_config.json:β100%"
+ }
+ },
+ "45cdaabb1a25494da00671d8a61cca02": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_7b44f7389e374bc496a71a43f31f9a93",
+ "max": 170,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_c616b6c74fa54db281d51621c0956afb",
+ "value": 170
+ }
+ },
+ "bd1957ea932d4365b314044dbcc904f7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_40e919a3a8424396b29817cfac983a19",
+ "placeholder": "β",
+ "style": "IPY_MODEL_c352b23d93ea481c9db8989435987387",
+ "value": "β170/170β[00:00<00:00,β3.93kB/s]"
+ }
+ },
+ "2eb96730c5ec4bc6abbc4e6fde479904": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "112b11adf39344558b2dbc62b2f2c34e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "268a421a0ce348c6a0221dabf2aab752": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "7b44f7389e374bc496a71a43f31f9a93": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c616b6c74fa54db281d51621c0956afb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "40e919a3a8424396b29817cfac983a19": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c352b23d93ea481c9db8989435987387": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "898310a70e1a41c6a78db36b15872139": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_26fe07f543a2443b9718c9bcfd4c7cef",
+ "IPY_MODEL_3a65a0c044374eae8d1b52ea616c6966",
+ "IPY_MODEL_6d245e8636004060ae64fc6b4b66dc4a"
+ ],
+ "layout": "IPY_MODEL_75e69c2aef4247b0b8483f339074e4b2"
+ }
+ },
+ "26fe07f543a2443b9718c9bcfd4c7cef": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_7250f0abd0dc4a8ca3c22283b9b95196",
+ "placeholder": "β",
+ "style": "IPY_MODEL_cac1c352fe3242e3876792d8cf8e152b",
+ "value": "model-00001-of-00002.safetensors:β100%"
+ }
+ },
+ "3a65a0c044374eae8d1b52ea616c6966": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "danger",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_904a33f29a2d4a3bb91509200bce9ae8",
+ "max": 4977149239,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_1ecd9be8e8a24f88aaed902fc2184eac",
+ "value": 4977148765
+ }
+ },
+ "6d245e8636004060ae64fc6b4b66dc4a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_ccb430e8f704472e9c57205516bdcb2d",
+ "placeholder": "β",
+ "style": "IPY_MODEL_798afe127b084fe0a91d17ada5f43100",
+ "value": "β4.98G/4.98Gβ[00:54<00:00,β188MB/s]"
+ }
+ },
+ "75e69c2aef4247b0b8483f339074e4b2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "7250f0abd0dc4a8ca3c22283b9b95196": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "cac1c352fe3242e3876792d8cf8e152b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "904a33f29a2d4a3bb91509200bce9ae8": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1ecd9be8e8a24f88aaed902fc2184eac": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "ccb430e8f704472e9c57205516bdcb2d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "798afe127b084fe0a91d17ada5f43100": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "8f0a82cfc58a4e5aa4d627c3617e3f3c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_7c88f888c58b4983b32511fff78106f8",
+ "IPY_MODEL_a41bb3352ea64ec6ad5c28f8fe0e4551",
+ "IPY_MODEL_bcfa74c9f55a405aa7cc38264b446306"
+ ],
+ "layout": "IPY_MODEL_9a157adf02b44e549aa462862ab56efc"
+ }
+ },
+ "7c88f888c58b4983b32511fff78106f8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_decddbf4eaa14c98ae66c47afc97ca45",
+ "placeholder": "β",
+ "style": "IPY_MODEL_d63a25bdfda24843a2650f1856f4f69c",
+ "value": "model-00002-of-00002.safetensors:β100%"
+ }
+ },
+ "a41bb3352ea64ec6ad5c28f8fe0e4551": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "danger",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b757336bb39649d38554d6ef46bc2256",
+ "max": 4111516960,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_a3b20c6c461e481ab7b3c5df55274d91",
+ "value": 4111516568
+ }
+ },
+ "bcfa74c9f55a405aa7cc38264b446306": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_65d8ca0e51c544fdaaacc32f1acbf3fe",
+ "placeholder": "β",
+ "style": "IPY_MODEL_ccc94bb9f682477586ab5629a97fc6a4",
+ "value": "β4.11G/4.11Gβ[01:29<00:00,β62.6MB/s]"
+ }
+ },
+ "9a157adf02b44e549aa462862ab56efc": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "decddbf4eaa14c98ae66c47afc97ca45": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d63a25bdfda24843a2650f1856f4f69c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "b757336bb39649d38554d6ef46bc2256": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "a3b20c6c461e481ab7b3c5df55274d91": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "65d8ca0e51c544fdaaacc32f1acbf3fe": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ccc94bb9f682477586ab5629a97fc6a4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "95d2323a7f1943b79f617f9b8ea2a6da": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_af9563ee1ec84bf0badf7b85de531e0c",
+ "IPY_MODEL_394dc8bcbd3349c0afcf622d4e2a5fd9",
+ "IPY_MODEL_9f48cf0aca80435f89ec30c72f3393ba"
+ ],
+ "layout": "IPY_MODEL_137feb39a3e943b3823018f328c63cbe"
+ }
+ },
+ "af9563ee1ec84bf0badf7b85de531e0c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_f49ebeaf150c4a72b0d86218e5ff4850",
+ "placeholder": "β",
+ "style": "IPY_MODEL_8991569c58ab413c98416c05bc79f2d9",
+ "value": ""
+ }
+ },
+ "394dc8bcbd3349c0afcf622d4e2a5fd9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_7b6fe5895b7249b7a8c9af48723ffcb2",
+ "max": 2,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_50d2e33de27443e4b66b78c7edb02865",
+ "value": 2
+ }
+ },
+ "9f48cf0aca80435f89ec30c72f3393ba": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_f529590d62b54546acf21e6e6954ada7",
+ "placeholder": "β",
+ "style": "IPY_MODEL_bf64273a481447c6ab170b58c038370e",
+ "value": "Loadingβsafetensorsβcheckpointβshards:β100%βCompletedβ|β2/2β[00:45<00:00,β22.26s/it]\n"
+ }
+ },
+ "137feb39a3e943b3823018f328c63cbe": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "f49ebeaf150c4a72b0d86218e5ff4850": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "8991569c58ab413c98416c05bc79f2d9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "7b6fe5895b7249b7a8c9af48723ffcb2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "50d2e33de27443e4b66b78c7edb02865": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "f529590d62b54546acf21e6e6954ada7": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "bf64273a481447c6ab170b58c038370e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "8054c7c25be44345a5f93fc1041ef6aa": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_e9dea3d189c64987b70a2b993138a5b8",
+ "IPY_MODEL_88f7bc62bba74221a9bfd1d64b59927e",
+ "IPY_MODEL_0e2a50c346164248b83991be238df301"
+ ],
+ "layout": "IPY_MODEL_dadba4e34cb74ca98ab9b25bbaae4f97"
+ }
+ },
+ "e9dea3d189c64987b70a2b993138a5b8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d111bd033f984e248c035fe294a873cd",
+ "placeholder": "β",
+ "style": "IPY_MODEL_1ac166a037234cdab5fe781951e17d9a",
+ "value": ""
+ }
+ },
+ "88f7bc62bba74221a9bfd1d64b59927e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_189b3a15851948e5a668b76570dc9298",
+ "max": 2,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_c163230a1ab549bda6ee48d17f1f25f8",
+ "value": 2
+ }
+ },
+ "0e2a50c346164248b83991be238df301": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_0623fb8426f9490199431d16730827d8",
+ "placeholder": "β",
+ "style": "IPY_MODEL_df18562664e6464b877627df1c881f9e",
+ "value": "Loadingβsafetensorsβcheckpointβshards:β100%βCompletedβ|β2/2β[00:44<00:00,β21.94s/it]\n"
+ }
+ },
+ "dadba4e34cb74ca98ab9b25bbaae4f97": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d111bd033f984e248c035fe294a873cd": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1ac166a037234cdab5fe781951e17d9a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "189b3a15851948e5a668b76570dc9298": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c163230a1ab549bda6ee48d17f1f25f8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "0623fb8426f9490199431d16730827d8": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "df18562664e6464b877627df1c881f9e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "fa6c3f077e46489897d00052dc9fa748": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_8715b1eb6d45493f975ae7edae037f85",
+ "IPY_MODEL_9d262bb6433840f8aded127518a84658",
+ "IPY_MODEL_138acd329cd14a9a9b3f80bd2b0e7221"
+ ],
+ "layout": "IPY_MODEL_dfb878bea074453fa4420bcd0adf419d"
+ }
+ },
+ "8715b1eb6d45493f975ae7edae037f85": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_022e0ee46e124805be1fcbf38546bd56",
+ "placeholder": "β",
+ "style": "IPY_MODEL_1160e67aacb7462e9a629aeeec5e3d86",
+ "value": "tokenizer_config.json:β100%"
+ }
+ },
+ "9d262bb6433840f8aded127518a84658": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b71100db84c545da9a7049e3479cf0e1",
+ "max": 17989,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_138e3ee362eb49a48e7f4c3a82d505fd",
+ "value": 17989
+ }
+ },
+ "138acd329cd14a9a9b3f80bd2b0e7221": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_2da48d73f0d24befa001bd8ce83564e9",
+ "placeholder": "β",
+ "style": "IPY_MODEL_053df1a83af249e0b4a2a1d7d8f7b656",
+ "value": "β18.0k/18.0kβ[00:00<00:00,β1.42MB/s]"
+ }
+ },
+ "dfb878bea074453fa4420bcd0adf419d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "022e0ee46e124805be1fcbf38546bd56": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1160e67aacb7462e9a629aeeec5e3d86": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "b71100db84c545da9a7049e3479cf0e1": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "138e3ee362eb49a48e7f4c3a82d505fd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "2da48d73f0d24befa001bd8ce83564e9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "053df1a83af249e0b4a2a1d7d8f7b656": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "b2f4bcc18a7c4a999dace66601368a02": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_3982c5c4a1e7497f9645e3f52aecf2b5",
+ "IPY_MODEL_5f88d3f1cc26462aa57c5abe6653d2b2",
+ "IPY_MODEL_b4487ca6b8b64d09ace434c23c786391"
+ ],
+ "layout": "IPY_MODEL_304abe1703954d32a9b38dc16c6c9b2a"
+ }
+ },
+ "3982c5c4a1e7497f9645e3f52aecf2b5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_1b6ec3d23a3e43c3b027a7882ffa68ff",
+ "placeholder": "β",
+ "style": "IPY_MODEL_d724e1316a7149b8b9c1c1f0a09fd78a",
+ "value": "vocab.json:β100%"
+ }
+ },
+ "5f88d3f1cc26462aa57c5abe6653d2b2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_a297ec50c313419380e563823557e7d7",
+ "max": 1612637,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_8eeedd15a5a94290ae0cb9a97f6a05f2",
+ "value": 1612637
+ }
+ },
+ "b4487ca6b8b64d09ace434c23c786391": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_3c21343548944949bde672be75f55652",
+ "placeholder": "β",
+ "style": "IPY_MODEL_ac09b943e8444a8db305053b36da20d6",
+ "value": "β1.61M/1.61Mβ[00:00<00:00,β2.67MB/s]"
+ }
+ },
+ "304abe1703954d32a9b38dc16c6c9b2a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1b6ec3d23a3e43c3b027a7882ffa68ff": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d724e1316a7149b8b9c1c1f0a09fd78a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "a297ec50c313419380e563823557e7d7": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "8eeedd15a5a94290ae0cb9a97f6a05f2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "3c21343548944949bde672be75f55652": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ac09b943e8444a8db305053b36da20d6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "2fdedcfc3c27456ca35f6d1346605b41": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_20d5635fb1084f5fa2a093ae07b92a93",
+ "IPY_MODEL_2b6e4cd7dfba4dafaedcd23bdecf1a83",
+ "IPY_MODEL_3497f075cf834fbdafa9a93614e8a0e8"
+ ],
+ "layout": "IPY_MODEL_5ed334a793d346df9fd82789d03d1081"
+ }
+ },
+ "20d5635fb1084f5fa2a093ae07b92a93": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_ccdd7ba41f214995ad302911ced5cc5e",
+ "placeholder": "β",
+ "style": "IPY_MODEL_2cccb494761b478781129aad28f475c7",
+ "value": "merges.txt:β100%"
+ }
+ },
+ "2b6e4cd7dfba4dafaedcd23bdecf1a83": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_e0e7827aea4f4a7e9d9e31a01e44b9cc",
+ "max": 916646,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_e0b71444938347a8a9d023d1e9a31b0b",
+ "value": 916646
+ }
+ },
+ "3497f075cf834fbdafa9a93614e8a0e8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_2f0d9d575f724badb3c20df69cedec5a",
+ "placeholder": "β",
+ "style": "IPY_MODEL_edce818ad915499bb268f5072fd51712",
+ "value": "β917k/917kβ[00:00<00:00,β2.07MB/s]"
+ }
+ },
+ "5ed334a793d346df9fd82789d03d1081": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ccdd7ba41f214995ad302911ced5cc5e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "2cccb494761b478781129aad28f475c7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "e0e7827aea4f4a7e9d9e31a01e44b9cc": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "e0b71444938347a8a9d023d1e9a31b0b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "2f0d9d575f724badb3c20df69cedec5a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "edce818ad915499bb268f5072fd51712": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "3e0ebb372f3e4217a5483367f9b6ff7b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_e467dcde83854d889ef02e2c7549c914",
+ "IPY_MODEL_2481bdc4e0ab4e9a8868d9d3d998a733",
+ "IPY_MODEL_6a1c470af59e4568b3e23cba91eb9ac0"
+ ],
+ "layout": "IPY_MODEL_573f0bb6bcbc4af8a1703277316cf572"
+ }
+ },
+ "e467dcde83854d889ef02e2c7549c914": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_79f47fbfccbb4fa88358df6fe018d4c9",
+ "placeholder": "β",
+ "style": "IPY_MODEL_da57411861e9458893bb1c3aa39c1d4f",
+ "value": "special_tokens_map.json:β100%"
+ }
+ },
+ "2481bdc4e0ab4e9a8868d9d3d998a733": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d5d6dca20c874a8eb7bff7871712e6d8",
+ "max": 570,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_1cfd941419c644f48a7a7abd19dc1a5a",
+ "value": 570
+ }
+ },
+ "6a1c470af59e4568b3e23cba91eb9ac0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_a5eec47d513945f3a253b177e0a35728",
+ "placeholder": "β",
+ "style": "IPY_MODEL_a1ce8099c7384797bde75e1f6db8f3be",
+ "value": "β570/570β[00:00<00:00,β46.7kB/s]"
+ }
+ },
+ "573f0bb6bcbc4af8a1703277316cf572": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "79f47fbfccbb4fa88358df6fe018d4c9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "da57411861e9458893bb1c3aa39c1d4f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "d5d6dca20c874a8eb7bff7871712e6d8": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "1cfd941419c644f48a7a7abd19dc1a5a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "a5eec47d513945f3a253b177e0a35728": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "a1ce8099c7384797bde75e1f6db8f3be": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c340a432936344d9ad48b09ea3eb629c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_9489548ea7144b8ca8ceeeac5aff2229",
+ "IPY_MODEL_f0b50d31dfaf46a3978deaec21e07d3c",
+ "IPY_MODEL_cc4dc41f111f493796ec6e12af0828bc"
+ ],
+ "layout": "IPY_MODEL_0b4326b140274671afe106409e7396ff"
+ }
+ },
+ "9489548ea7144b8ca8ceeeac5aff2229": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_62931487994b45d38e3be0c27916ac03",
+ "placeholder": "β",
+ "style": "IPY_MODEL_71b6557b3e294946895dc7cb37a8696d",
+ "value": "tokenizer.json:β100%"
+ }
+ },
+ "f0b50d31dfaf46a3978deaec21e07d3c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c2c396e31cec4ae1b374e06c979abadf",
+ "max": 7153264,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_dfad1aac01a5423883dea57385827a35",
+ "value": 7153264
+ }
+ },
+ "cc4dc41f111f493796ec6e12af0828bc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d64fefcc50b64da0bd2349928fb182ab",
+ "placeholder": "β",
+ "style": "IPY_MODEL_677baf0c62774d6598e035e5d24a2d00",
+ "value": "β7.15M/7.15Mβ[00:00<00:00,β21.3MB/s]"
+ }
+ },
+ "0b4326b140274671afe106409e7396ff": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "62931487994b45d38e3be0c27916ac03": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "71b6557b3e294946895dc7cb37a8696d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c2c396e31cec4ae1b374e06c979abadf": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "dfad1aac01a5423883dea57385827a35": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "d64fefcc50b64da0bd2349928fb182ab": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "677baf0c62774d6598e035e5d24a2d00": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "07b30751d3f3444d835031a204bdb2e0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_3e0103dfdf38443ba43aeaf6abdf3265",
+ "IPY_MODEL_db42a3d5b00d4024ac55ab1889a66fb9",
+ "IPY_MODEL_458a05b30f2c476698e58df1d8924acb"
+ ],
+ "layout": "IPY_MODEL_13b27280a90041a883df4f0bfc2f9cd2"
+ }
+ },
+ "3e0103dfdf38443ba43aeaf6abdf3265": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_ffe6fa7a932d47c6a3eb9530cd37d446",
+ "placeholder": "β",
+ "style": "IPY_MODEL_5e6a16df45884d02a69cb6c18d895c50",
+ "value": "README.md:β100%"
+ }
+ },
+ "db42a3d5b00d4024ac55ab1889a66fb9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_10c0a63663144971b236882975b1ca8e",
+ "max": 7940,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_6e7e2cfc6f734f05832f49e1e60ae03e",
+ "value": 7940
+ }
+ },
+ "458a05b30f2c476698e58df1d8924acb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_bcddf8f0866347868641450c62bc1957",
+ "placeholder": "β",
+ "style": "IPY_MODEL_edfa5c630d234c0d914de21682e5d888",
+ "value": "β7.94k/7.94kβ[00:00<00:00,β563kB/s]"
+ }
+ },
+ "13b27280a90041a883df4f0bfc2f9cd2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ffe6fa7a932d47c6a3eb9530cd37d446": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "5e6a16df45884d02a69cb6c18d895c50": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "10c0a63663144971b236882975b1ca8e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "6e7e2cfc6f734f05832f49e1e60ae03e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "bcddf8f0866347868641450c62bc1957": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "edfa5c630d234c0d914de21682e5d888": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c2ce21915c9c4b4588080c48986a5e17": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_d871c30fbc0a4320ba212f2b90961390",
+ "IPY_MODEL_ea7e8a0625a4469e911acb4f527f0f7e",
+ "IPY_MODEL_0647391c490e4d4a9e5d248e12524c39"
+ ],
+ "layout": "IPY_MODEL_33f7f164af0843438941cb65d3413be1"
+ }
+ },
+ "d871c30fbc0a4320ba212f2b90961390": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_6ae9e5c88f754e6196c1f443b3adfa21",
+ "placeholder": "β",
+ "style": "IPY_MODEL_28a2b6bbaf564e4f91b20931987dd27b",
+ "value": "train-00000-of-00001.parquet:β100%"
+ }
+ },
+ "ea7e8a0625a4469e911acb4f527f0f7e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_199355ae41414756b27f6dbc2ba5620d",
+ "max": 2306545,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_60663929460c484eb466f232784e711c",
+ "value": 2306545
+ }
+ },
+ "0647391c490e4d4a9e5d248e12524c39": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_962fbde200684096aeb69efde0c7ab57",
+ "placeholder": "β",
+ "style": "IPY_MODEL_31ef4562f7774dca949205c5562a2149",
+ "value": "β2.31M/2.31Mβ[00:00<00:00,β26.0MB/s]"
+ }
+ },
+ "33f7f164af0843438941cb65d3413be1": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "6ae9e5c88f754e6196c1f443b3adfa21": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "28a2b6bbaf564e4f91b20931987dd27b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "199355ae41414756b27f6dbc2ba5620d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "60663929460c484eb466f232784e711c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "962fbde200684096aeb69efde0c7ab57": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "31ef4562f7774dca949205c5562a2149": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "916effa56405485ea8a43e47669d9035": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_3d60fd796c8b443cba248de98a80e8c4",
+ "IPY_MODEL_58b4d0041fde48a38d2d6555a4c3e95a",
+ "IPY_MODEL_2bfa3f7520df46f49c749de3e8002926"
+ ],
+ "layout": "IPY_MODEL_7668c14dc1904018b9726103f5b92511"
+ }
+ },
+ "3d60fd796c8b443cba248de98a80e8c4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_ffb4335d274d449dbcbee2d6aea8dbfb",
+ "placeholder": "β",
+ "style": "IPY_MODEL_f89d5dae5006481191f7123b19eb4d3e",
+ "value": "test-00000-of-00001.parquet:β100%"
+ }
+ },
+ "58b4d0041fde48a38d2d6555a4c3e95a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_6d8a85478b0b4424a84a389851df6554",
+ "max": 419088,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_91628b0f3801439989d6014cace043cc",
+ "value": 419088
+ }
+ },
+ "2bfa3f7520df46f49c749de3e8002926": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_dfa4fc6f471f4027ad87ae865c49da5e",
+ "placeholder": "β",
+ "style": "IPY_MODEL_2f706a61e19547d7a0ae53cc96227eb2",
+ "value": "β419k/419kβ[00:00<00:00,β25.0MB/s]"
+ }
+ },
+ "7668c14dc1904018b9726103f5b92511": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ffb4335d274d449dbcbee2d6aea8dbfb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "f89d5dae5006481191f7123b19eb4d3e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "6d8a85478b0b4424a84a389851df6554": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "91628b0f3801439989d6014cace043cc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "dfa4fc6f471f4027ad87ae865c49da5e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "2f706a61e19547d7a0ae53cc96227eb2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "eb107bdd4867400d99dfe332a190a419": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_ab4dfebe8d2948bba5e4ada27a543944",
+ "IPY_MODEL_7c91e824950d4fe0bf3f5b8c4d803274",
+ "IPY_MODEL_3e06a676bde54989918fd2e553fc0bac"
+ ],
+ "layout": "IPY_MODEL_a17709ae6e7646719ba80a40627286f9"
+ }
+ },
+ "ab4dfebe8d2948bba5e4ada27a543944": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_204c4ad9ed2d45c8a9b148e061a46ffa",
+ "placeholder": "β",
+ "style": "IPY_MODEL_2dfdf4441b104abc87683488a43cd4c7",
+ "value": "Generatingβtrainβsplit:β100%"
+ }
+ },
+ "7c91e824950d4fe0bf3f5b8c4d803274": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d1ce3b6a25034044b61a7d4d4f81b1a2",
+ "max": 7473,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_8b72be4ef1054194978a4222155fbc56",
+ "value": 7473
+ }
+ },
+ "3e06a676bde54989918fd2e553fc0bac": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_64d8c1496ae14364a51fa4127f42ff71",
+ "placeholder": "β",
+ "style": "IPY_MODEL_9efcb1c8f86040dab38c969773229a4f",
+ "value": "β7473/7473β[00:00<00:00,β6085.55βexamples/s]"
+ }
+ },
+ "a17709ae6e7646719ba80a40627286f9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "204c4ad9ed2d45c8a9b148e061a46ffa": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "2dfdf4441b104abc87683488a43cd4c7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "d1ce3b6a25034044b61a7d4d4f81b1a2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "8b72be4ef1054194978a4222155fbc56": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "64d8c1496ae14364a51fa4127f42ff71": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "9efcb1c8f86040dab38c969773229a4f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "7a4ba2775ea042c09440feda17af8547": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_80687fd47d114b94972671535162df18",
+ "IPY_MODEL_f217fde868194c88a9bcf25cf68da353",
+ "IPY_MODEL_c5c423ff63f84780a65e9871c4b16b54"
+ ],
+ "layout": "IPY_MODEL_ddeccde7c52c4f3e99e25f5713a2bd30"
+ }
+ },
+ "80687fd47d114b94972671535162df18": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_b1c1d47ce3a447c5b566aac8293ee920",
+ "placeholder": "β",
+ "style": "IPY_MODEL_472011119aa8443082082f32e5cdcead",
+ "value": "Generatingβtestβsplit:β100%"
+ }
+ },
+ "f217fde868194c88a9bcf25cf68da353": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_dbf87fa697f64c939953d5ee43c3451d",
+ "max": 1319,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_edd877fc1cec47c79a7bfc66353878f6",
+ "value": 1319
+ }
+ },
+ "c5c423ff63f84780a65e9871c4b16b54": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_3a78e3ab794f4171a1f5340ae6bb3463",
+ "placeholder": "β",
+ "style": "IPY_MODEL_c2d385cb15f245fbbfe997ee9521ebcb",
+ "value": "β1319/1319β[00:00<00:00,β63091.30βexamples/s]"
+ }
+ },
+ "ddeccde7c52c4f3e99e25f5713a2bd30": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "b1c1d47ce3a447c5b566aac8293ee920": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "472011119aa8443082082f32e5cdcead": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "dbf87fa697f64c939953d5ee43c3451d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "edd877fc1cec47c79a7bfc66353878f6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "3a78e3ab794f4171a1f5340ae6bb3463": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "c2d385cb15f245fbbfe997ee9521ebcb": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "786a033ddff343288d53cd29436e1c6e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HBoxModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HBoxModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HBoxView",
+ "box_style": "",
+ "children": [
+ "IPY_MODEL_ff97c955f459472ead1d7a0855d7db6e",
+ "IPY_MODEL_8e015ff487584563b4af1cde693e9ad2",
+ "IPY_MODEL_94ea5740d07f4ae1abd2f494aed82ede"
+ ],
+ "layout": "IPY_MODEL_b992b5106cb14b9e8c01883d303203a0"
+ }
+ },
+ "ff97c955f459472ead1d7a0855d7db6e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_d0c02c0ed31b4c3fbb0244b4be2f703a",
+ "placeholder": "β",
+ "style": "IPY_MODEL_0575d12e030e40beabba0b4c53e843c7",
+ "value": "Map:β100%"
+ }
+ },
+ "8e015ff487584563b4af1cde693e9ad2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "FloatProgressModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "FloatProgressModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "ProgressView",
+ "bar_style": "success",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_c7e27fcad0724914877fbef99d2ee498",
+ "max": 7473,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_ff8d48a49166403caafbb9971588bee5",
+ "value": 7473
+ }
+ },
+ "94ea5740d07f4ae1abd2f494aed82ede": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "HTMLModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "HTMLModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "HTMLView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_fd4ef85c288a40f1a2beb1097a798909",
+ "placeholder": "β",
+ "style": "IPY_MODEL_3cf01e74e4964cf8b5347c6f517e05f4",
+ "value": "β7473/7473β[00:00<00:00,β18236.38βexamples/s]"
+ }
+ },
+ "b992b5106cb14b9e8c01883d303203a0": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "d0c02c0ed31b4c3fbb0244b4be2f703a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "0575d12e030e40beabba0b4c53e843c7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ },
+ "c7e27fcad0724914877fbef99d2ee498": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "ff8d48a49166403caafbb9971588bee5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "ProgressStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "ProgressStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "bar_color": null,
+ "description_width": ""
+ }
+ },
+ "fd4ef85c288a40f1a2beb1097a798909": {
+ "model_module": "@jupyter-widgets/base",
+ "model_name": "LayoutModel",
+ "model_module_version": "1.2.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/base",
+ "_model_module_version": "1.2.0",
+ "_model_name": "LayoutModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "LayoutView",
+ "align_content": null,
+ "align_items": null,
+ "align_self": null,
+ "border": null,
+ "bottom": null,
+ "display": null,
+ "flex": null,
+ "flex_flow": null,
+ "grid_area": null,
+ "grid_auto_columns": null,
+ "grid_auto_flow": null,
+ "grid_auto_rows": null,
+ "grid_column": null,
+ "grid_gap": null,
+ "grid_row": null,
+ "grid_template_areas": null,
+ "grid_template_columns": null,
+ "grid_template_rows": null,
+ "height": null,
+ "justify_content": null,
+ "justify_items": null,
+ "left": null,
+ "margin": null,
+ "max_height": null,
+ "max_width": null,
+ "min_height": null,
+ "min_width": null,
+ "object_fit": null,
+ "object_position": null,
+ "order": null,
+ "overflow": null,
+ "overflow_x": null,
+ "overflow_y": null,
+ "padding": null,
+ "right": null,
+ "top": null,
+ "visibility": null,
+ "width": null
+ }
+ },
+ "3cf01e74e4964cf8b5347c6f517e05f4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_name": "DescriptionStyleModel",
+ "model_module_version": "1.5.0",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ }
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
\ No newline at end of file
| | |