Add files using upload-large-folder tool

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+language:
+  - en
+tags:
+  - spark-gpt
+  - qwen3-moe
+  - from-scratch
+  - stories
+  - checkpoints
+---
+
+# Lil Bard historical checkpoints
+
+This repository contains 25 loadable Transformers checkpoints from the
+pretraining run for [`N8Programs/lil-bard`](https://huggingface.co/N8Programs/lil-bard).
+The final step-25,485 model is kept in that separate repository so ordinary
+users do not download the full checkpoint history.
+
+Checkpoints span step 1,000 through step 25,000 in increments of 1,000. Each
+subfolder contains a complete `Qwen3MoeForCausalLM` export and tokenizer.
+
+## Loading a checkpoint
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = "N8Programs/lil-bard-checkpts"
+subfolder = "step-00010000"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder=subfolder)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_id,
+    subfolder=subfolder,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+```
+
+Available subfolders are `step-00001000`, `step-00002000`, ..., through
+`step-00025000`.
+
+## Run summary
+
+Lil Bard is a 172,052,992-parameter English story MoE with 58,806,784 active
+parameters per token, 8 experts with top-2 routing, and an 8,192-entry
+whole-document byte-level BPE tokenizer. It was pretrained from scratch for
+2,492,032,616 real loss tokens on two NVIDIA GB10 systems.
+
+The final model, architecture and data details, evaluations, usage example,
+and limitations are documented in the
+[`N8Programs/lil-bard` model card](https://huggingface.co/N8Programs/lil-bard).
+The complete training trace is available in the
+[`lil_bard_moe_8x2_full` W&B run](https://wandb.ai/n8programs/sparkgpt/runs/mxk8gln1).
+
+Only model exports are included here. The larger optimizer/scheduler resume
+checkpoints are not uploaded.

step-0002000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0003000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0003000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0003000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0005000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0005000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0005000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0007000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0007000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0007000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0008000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0008000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0008000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0010000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0010000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0010000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0011000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0011000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0011000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0013000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0013000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0013000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0015000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0015000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0015000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0017000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0017000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0017000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0018000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0018000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0018000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0020000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0020000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0020000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}

step-0024000/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "model_type": "qwen3_moe",
+  "vocab_size": 8192,
+  "hidden_size": 512,
+  "num_hidden_layers": 16,
+  "intermediate_size": 1536,
+  "num_attention_heads": 4,
+  "num_key_value_heads": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 32768,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191,
+  "torch_dtype": "float32",
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 768,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "norm_topk_prob": true,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "mlp_only_layers": [],
+  "use_sliding_window": false,
+  "sliding_window": null
+}

step-0024000/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 8190,
+  "eos_token_id": 0,
+  "pad_token_id": 8191
+}

step-0024000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|beginoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "model_max_length": 32768,
+  "clean_up_tokenization_spaces": false,
+  "unk_token": "<|unk|>"
+}