Add files using upload-large-folder tool

README.md

@@ -1,3 +1,209 @@
----
-license: apache-2.0
----
+# Mini GLM 5.2 Active-MTP Debug Checkpoint, FP8
+
+This is a small GLM-5.2-style checkpoint built for inference plumbing and kernel
+debugging, not for model quality. This directory is the FP8 weight-quantized
+variant of the active-MTP full-dimension checkpoint.
+
+The base model is a 14-layer mini GLM-MoE-DSA model trained for readable English.
+It has been upscaled to GLM-5.2-compatible tensor dimensions and includes one
+appended MTP/EAGLE next-token layer for SGLang speculative decoding.
+
+The FP8 export follows the public GLM-5.2-FP8 checkpoint convention:
+
+- eligible 2D linear weights are stored as `torch.float8_e4m3fn`
+- each quantized weight has a sibling `*_scale_inv` tensor
+- scale tensors are FP32 with 128x128 block granularity
+- embeddings, norms, router gates, DSA `weights_proj`, and MTP glue
+  projections/norms remain unquantized
+
+## Intended Use
+
+- Debug SGLang GLM-MoE-DSA inference without loading the full GLM 5.2 model.
+- Exercise DSA, MoE, attention, TP sharding, FP8 KV cache, and EAGLE/MTP paths.
+- Validate kernel changes against a checkpoint that is small in layer count but
+  keeps GLM-5.2-like shapes.
+
+This model is expected to produce readable but repetitive English. It is not a
+general-purpose language model.
+
+## MTP Details
+
+The appended MTP layer is active and nonzero. Its attention and MoE tensors were
+trained, rather than zeroed out, so this checkpoint can exercise the MTP decoder
+attention/MoE path during serving.
+
+The MTP trainer uses SGLang EAGLE nextn alignment:
+
+```text
+hidden[t] + token[t+1] -> token[t+2]
+```
+
+For rollout step `k`:
+
+```text
+input token = token[t+k+1]
+target      = token[t+k+2]
+```
+
+This is intentionally not the standard LM shift
+`hidden[t] + token[t] -> token[t+1]`.
+
+## Compatibility
+
+### SGLang
+
+This directory is intended for SGLang serving with GLM-MoE-DSA, TileLang DSA,
+FP8 KV cache, and EAGLE speculative decoding.
+
+Example shape of the serving command:
+
+```bash
+source ./ENV_RUN.sh
+CUDA_VISIBLE_DEVICES=6,7 HIP_VISIBLE_DEVICES=6,7 sglang serve \
+  --model-path /root/inference-v2/mini-glm-5.2/v1c-upscale/checkpoints/v1b-mtp-active-decoder-serveddata-align-1k-full-original-dims-tiled-sglang-fp8 \
+  --tp 2 \
+  --trust-remote-code \
+  --dsa-prefill-backend tilelang \
+  --dsa-decode-backend tilelang \
+  --kv-cache-dtype fp8_e4m3 \
+  --chunked-prefill-size 4096 \
+  --max-total-tokens 4096 \
+  --speculative-algorithm EAGLE \
+  --speculative-num-steps 3 \
+  --speculative-eagle-topk 1 \
+  --speculative-num-draft-tokens 4 \
+  --disable-custom-all-reduce \
+  --disable-shared-experts-fusion \
+  --cuda-graph-backend-decode disabled \
+  --cuda-graph-backend-prefill disabled
+```
+
+### Hugging Face Transformers
+
+Use the BF16/full-dimension checkpoint for Hugging Face Transformers CPU/GPU
+reference inference. This FP8 directory is intended for SGLang's GLM FP8 loader.
+The FP8 tensors match the GLM-5.2-FP8 safetensors layout, but generic HF
+Transformers inference may not dequantize this custom GLM-MoE-DSA FP8 format.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+path = "/root/inference-v2/mini-glm-5.2/v1c-upscale/checkpoints/v1b-mtp-active-decoder-serveddata-align-1k-full-original-dims-tiled-sglang"
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(path, trust_remote_code=True)
+```
+
+HF inference uses only the base 14-layer causal LM. The appended MTP tensors are
+reported as unexpected keys because HF Transformers' `glm_moe_dsa` model does
+not implement the MTP/EAGLE nextn path.
+
+## Training Summary
+
+The MTP layer was trained from copied active decoder weights with the corrected
+SGLang EAGLE alignment on a small SGLang-served token dataset.
+
+Final offline served-data metrics for the source MTP checkpoint:
+
+| Metric | Value |
+|---|---:|
+| accept@0 | 0.9295 |
+| accept@1 | 0.8760 |
+| accept@2 | 0.8292 |
+| average accepted draft tokens | 2.6346 |
+| data loss | 0.7798 |
+
+These are offline metrics on the small served-token dataset and should be treated
+as a debugging signal, not a model-quality benchmark.
+
+## Example Outputs
+
+The model is only expected to produce barely passable English. Repetition,
+generic phrasing, weak reasoning, and topic drift are normal.
+
+Observed SGLang FP8 raw-completion sample:
+
+Prompt:
+
+```text
+A small language model is useful for testing inference code because
+```
+
+Response:
+
+```text
+it is an independent scientific method. However, the application of the
+language is considered as a social, practical approach. It has a wide range of
+specific characteristics and may be used for clinical practice.
+```
+
+The text is readable but semantically loose; that is the expected quality bar
+for this plumbing checkpoint.
+
+These examples show the intended quality bar: readable text for plumbing tests,
+not useful answers.
+
+### Example 1
+
+Prompt:
+
+```text
+The quick brown fox
+```
+
+Observed HF base-model response:
+
+```text
+The quick brown fox is a very good thing to do. It is a good thing to do.
+```
+
+### Example 2
+
+Prompt:
+
+```text
+Write one short paragraph about a library in a small town.
+```
+
+Expected style of response:
+
+```text
+The library is a quiet place in the center of the town. People come there to
+read books, ask questions, and sit at the tables in the afternoon. It is not a
+large building, but it is useful for the people who live nearby.
+```
+
+### Example 3
+
+Prompt:
+
+```text
+Explain why rain falls from clouds.
+```
+
+Expected style of response:
+
+```text
+Rain falls from clouds when water in the air becomes heavy enough to fall down.
+The cloud is made of small drops, and those drops can join together. When they
+become too heavy, they fall as rain.
+```
+
+### Example 4
+
+Prompt:
+
+```text
+Continue this sentence: The old machine started slowly because
+```
+
+Expected style of response:
+
+```text
+The old machine started slowly because the parts were worn and the motor needed
+time to move. It made a small sound, then a louder sound, and finally began to
+work again.
+```
+
+The responses above are coherent enough to inspect inference behavior, token
+flow, speculative decoding, and kernel changes. They should not be used to judge
+instruction following or factual accuracy.

config.json

@@ -0,0 +1,229 @@
+{
+  "architectures": [
+    "GlmMoeDsaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "ep_size": 1,
+  "first_k_dense_replace": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_share_for_mtp_iteration": true,
+  "index_skip_topk_offset": 3,
+  "index_topk": 2048,
+  "index_topk_freq": 4,
+  "index_topk_pattern": null,
+  "indexer_rope_interleave": true,
+  "indexer_types": [
+    "full",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full",
+    "shared",
+    "shared",
+    "shared",
+    "full"
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 16384,
+  "mlp_layer_types": [
+    "dense",
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "glm_moe_dsa",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "modules_to_not_convert": [
+      "lm_head",
+      "model.embed_tokens",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.indexer.k_norm",
+      "model.layers.0.self_attn.indexer.weights_proj",
+      "model.layers.0.self_attn.kv_a_layernorm",
+      "model.layers.0.self_attn.q_a_layernorm",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.indexer.k_norm",
+      "model.layers.1.self_attn.indexer.weights_proj",
+      "model.layers.1.self_attn.kv_a_layernorm",
+      "model.layers.1.self_attn.q_a_layernorm",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.indexer.k_norm",
+      "model.layers.10.self_attn.indexer.weights_proj",
+      "model.layers.10.self_attn.kv_a_layernorm",
+      "model.layers.10.self_attn.q_a_layernorm",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.indexer.k_norm",
+      "model.layers.11.self_attn.indexer.weights_proj",
+      "model.layers.11.self_attn.kv_a_layernorm",
+      "model.layers.11.self_attn.q_a_layernorm",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.indexer.k_norm",
+      "model.layers.12.self_attn.indexer.weights_proj",
+      "model.layers.12.self_attn.kv_a_layernorm",
+      "model.layers.12.self_attn.q_a_layernorm",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.indexer.k_norm",
+      "model.layers.13.self_attn.indexer.weights_proj",
+      "model.layers.13.self_attn.kv_a_layernorm",
+      "model.layers.13.self_attn.q_a_layernorm",
+      "model.layers.14.eh_proj",
+      "model.layers.14.enorm",
+      "model.layers.14.hnorm",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.indexer.k_norm",
+      "model.layers.14.self_attn.indexer.weights_proj",
+      "model.layers.14.self_attn.kv_a_layernorm",
+      "model.layers.14.self_attn.q_a_layernorm",
+      "model.layers.14.shared_head.norm",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.indexer.k_norm",
+      "model.layers.2.self_attn.indexer.weights_proj",
+      "model.layers.2.self_attn.kv_a_layernorm",
+      "model.layers.2.self_attn.q_a_layernorm",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.indexer.k_norm",
+      "model.layers.3.self_attn.indexer.weights_proj",
+      "model.layers.3.self_attn.kv_a_layernorm",
+      "model.layers.3.self_attn.q_a_layernorm",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.indexer.k_norm",
+      "model.layers.4.self_attn.indexer.weights_proj",
+      "model.layers.4.self_attn.kv_a_layernorm",
+      "model.layers.4.self_attn.q_a_layernorm",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.indexer.k_norm",
+      "model.layers.5.self_attn.indexer.weights_proj",
+      "model.layers.5.self_attn.kv_a_layernorm",
+      "model.layers.5.self_attn.q_a_layernorm",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.indexer.k_norm",
+      "model.layers.6.self_attn.indexer.weights_proj",
+      "model.layers.6.self_attn.kv_a_layernorm",
+      "model.layers.6.self_attn.q_a_layernorm",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.indexer.k_norm",
+      "model.layers.7.self_attn.indexer.weights_proj",
+      "model.layers.7.self_attn.kv_a_layernorm",
+      "model.layers.7.self_attn.q_a_layernorm",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.indexer.k_norm",
+      "model.layers.8.self_attn.indexer.weights_proj",
+      "model.layers.8.self_attn.kv_a_layernorm",
+      "model.layers.8.self_attn.q_a_layernorm",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.indexer.k_norm",
+      "model.layers.9.self_attn.indexer.weights_proj",
+      "model.layers.9.self_attn.kv_a_layernorm",
+      "model.layers.9.self_attn.q_a_layernorm",
+      "model.norm"
+    ],
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 8000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "5.12.0",
+  "use_cache": true,
+  "v1c_full_upscale": {
+    "active_attention_heads": 16,
+    "active_hidden_size": 1024,
+    "active_routed_experts": 16,
+    "expansion_strategy": "tiled active subspace with averaged input repeats",
+    "inactive_expert_bias": -1000000000.0,
+    "mtp_source_checkpoint": "/root/inference-v2/mini-glm-5.2/v1b-mtp/checkpoints/mtp-active-decoder-serveddata-align-1k/final",
+    "num_nextn_predict_layers": 1,
+    "source_checkpoint": "/root/inference-v2/mini-glm-5.2/v1a-mini-model/checkpoints/stage-b2-finewebedu16k-cont100m-2gpu/final",
+    "strict_equivalence_caveat": "RoPE 32->64 maps source frequencies into every-other target pair; unused target RoPE pairs are zero.",
+    "target_config": "/root/inference-v2/mini-glm-5.2/v1a-mini-model/config/glm-5.2-original-config.json"
+  },
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

fp8_quantization_report.json

@@ -0,0 +1,620 @@
+{
+  "block_size": [
+    128,
+    128
+  ],
+  "fp8_dtype": "torch.float8_e4m3fn",
+  "fp8_max": 448.0,
+  "modules_to_not_convert": [
+    "lm_head",
+    "model.embed_tokens",
+    "model.layers.0.input_layernorm",
+    "model.layers.0.post_attention_layernorm",
+    "model.layers.0.self_attn.indexer.k_norm",
+    "model.layers.0.self_attn.indexer.weights_proj",
+    "model.layers.0.self_attn.kv_a_layernorm",
+    "model.layers.0.self_attn.q_a_layernorm",
+    "model.layers.1.input_layernorm",
+    "model.layers.1.post_attention_layernorm",
+    "model.layers.1.self_attn.indexer.k_norm",
+    "model.layers.1.self_attn.indexer.weights_proj",
+    "model.layers.1.self_attn.kv_a_layernorm",
+    "model.layers.1.self_attn.q_a_layernorm",
+    "model.layers.10.input_layernorm",
+    "model.layers.10.mlp.gate",
+    "model.layers.10.post_attention_layernorm",
+    "model.layers.10.self_attn.indexer.k_norm",
+    "model.layers.10.self_attn.indexer.weights_proj",
+    "model.layers.10.self_attn.kv_a_layernorm",
+    "model.layers.10.self_attn.q_a_layernorm",
+    "model.layers.11.input_layernorm",
+    "model.layers.11.mlp.gate",
+    "model.layers.11.post_attention_layernorm",
+    "model.layers.11.self_attn.indexer.k_norm",
+    "model.layers.11.self_attn.indexer.weights_proj",
+    "model.layers.11.self_attn.kv_a_layernorm",
+    "model.layers.11.self_attn.q_a_layernorm",
+    "model.layers.12.input_layernorm",
+    "model.layers.12.mlp.gate",
+    "model.layers.12.post_attention_layernorm",
+    "model.layers.12.self_attn.indexer.k_norm",
+    "model.layers.12.self_attn.indexer.weights_proj",
+    "model.layers.12.self_attn.kv_a_layernorm",
+    "model.layers.12.self_attn.q_a_layernorm",
+    "model.layers.13.input_layernorm",
+    "model.layers.13.mlp.gate",
+    "model.layers.13.post_attention_layernorm",
+    "model.layers.13.self_attn.indexer.k_norm",
+    "model.layers.13.self_attn.indexer.weights_proj",
+    "model.layers.13.self_attn.kv_a_layernorm",
+    "model.layers.13.self_attn.q_a_layernorm",
+    "model.layers.14.eh_proj",
+    "model.layers.14.enorm",
+    "model.layers.14.hnorm",
+    "model.layers.14.input_layernorm",
+    "model.layers.14.mlp.gate",
+    "model.layers.14.post_attention_layernorm",
+    "model.layers.14.self_attn.indexer.k_norm",
+    "model.layers.14.self_attn.indexer.weights_proj",
+    "model.layers.14.self_attn.kv_a_layernorm",
+    "model.layers.14.self_attn.q_a_layernorm",
+    "model.layers.14.shared_head.norm",
+    "model.layers.2.input_layernorm",
+    "model.layers.2.mlp.gate",
+    "model.layers.2.post_attention_layernorm",
+    "model.layers.2.self_attn.indexer.k_norm",
+    "model.layers.2.self_attn.indexer.weights_proj",
+    "model.layers.2.self_attn.kv_a_layernorm",
+    "model.layers.2.self_attn.q_a_layernorm",
+    "model.layers.3.input_layernorm",
+    "model.layers.3.mlp.gate",
+    "model.layers.3.post_attention_layernorm",
+    "model.layers.3.self_attn.indexer.k_norm",
+    "model.layers.3.self_attn.indexer.weights_proj",
+    "model.layers.3.self_attn.kv_a_layernorm",
+    "model.layers.3.self_attn.q_a_layernorm",
+    "model.layers.4.input_layernorm",
+    "model.layers.4.mlp.gate",
+    "model.layers.4.post_attention_layernorm",
+    "model.layers.4.self_attn.indexer.k_norm",
+    "model.layers.4.self_attn.indexer.weights_proj",
+    "model.layers.4.self_attn.kv_a_layernorm",
+    "model.layers.4.self_attn.q_a_layernorm",
+    "model.layers.5.input_layernorm",
+    "model.layers.5.mlp.gate",
+    "model.layers.5.post_attention_layernorm",
+    "model.layers.5.self_attn.indexer.k_norm",
+    "model.layers.5.self_attn.indexer.weights_proj",
+    "model.layers.5.self_attn.kv_a_layernorm",
+    "model.layers.5.self_attn.q_a_layernorm",
+    "model.layers.6.input_layernorm",
+    "model.layers.6.mlp.gate",
+    "model.layers.6.post_attention_layernorm",
+    "model.layers.6.self_attn.indexer.k_norm",
+    "model.layers.6.self_attn.indexer.weights_proj",
+    "model.layers.6.self_attn.kv_a_layernorm",
+    "model.layers.6.self_attn.q_a_layernorm",
+    "model.layers.7.input_layernorm",
+    "model.layers.7.mlp.gate",
+    "model.layers.7.post_attention_layernorm",
+    "model.layers.7.self_attn.indexer.k_norm",
+    "model.layers.7.self_attn.indexer.weights_proj",
+    "model.layers.7.self_attn.kv_a_layernorm",
+    "model.layers.7.self_attn.q_a_layernorm",
+    "model.layers.8.input_layernorm",
+    "model.layers.8.mlp.gate",
+    "model.layers.8.post_attention_layernorm",
+    "model.layers.8.self_attn.indexer.k_norm",
+    "model.layers.8.self_attn.indexer.weights_proj",
+    "model.layers.8.self_attn.kv_a_layernorm",
+    "model.layers.8.self_attn.q_a_layernorm",
+    "model.layers.9.input_layernorm",
+    "model.layers.9.mlp.gate",
+    "model.layers.9.post_attention_layernorm",
+    "model.layers.9.self_attn.indexer.k_norm",
+    "model.layers.9.self_attn.indexer.weights_proj",
+    "model.layers.9.self_attn.kv_a_layernorm",
+    "model.layers.9.self_attn.q_a_layernorm",
+    "model.norm"
+  ],
+  "modules_to_not_convert_count": 110,
+  "output": "/root/inference-v2/mini-glm-5.2/v1c-upscale/checkpoints/v1b-mtp-active-decoder-serveddata-align-1k-full-original-dims-tiled-sglang-fp8",
+  "output_tensor_bytes": 133220606848,
+  "preserved_tensors": 138,
+  "quantized_tensors": 10134,
+  "scale_tensors": 10134,
+  "shards": [
+    {
+      "preserved": 8,
+      "quantized": 6,
+      "scale_tensors": 6,
+      "shard": "model-00001-of-00057.safetensors",
+      "tensor_bytes": 4046015104
+    },
+    {
+      "preserved": 20,
+      "quantized": 125,
+      "scale_tensors": 125,
+      "shard": "model-00002-of-00057.safetensors",
+      "tensor_bytes": 2149413376
+    },
+    {
+      "preserved": 16,
+      "quantized": 153,
+      "scale_tensors": 153,
+      "shard": "model-00003-of-00057.safetensors",
+      "tensor_bytes": 2141656640
+    },
+    {
+      "preserved": 18,
+      "quantized": 145,
+      "scale_tensors": 145,
+      "shard": "model-00004-of-00057.safetensors",
+      "tensor_bytes": 2140887360
+    },
+    {
+      "preserved": 19,
+      "quantized": 152,
+      "scale_tensors": 152,
+      "shard": "model-00005-of-00057.safetensors",
+      "tensor_bytes": 2104293376
+    },
+    {
+      "preserved": 44,
+      "quantized": 158,
+      "scale_tensors": 158,
+      "shard": "model-00006-of-00057.safetensors",
+      "tensor_bytes": 2152283904
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00007-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00008-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00009-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00010-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00011-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00012-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00013-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00014-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00015-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00016-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00017-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00018-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00019-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00020-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00021-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00022-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00023-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00024-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00025-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00026-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00027-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00028-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00029-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00030-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00031-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00032-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00033-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00034-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00035-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00036-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00037-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00038-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00039-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00040-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00041-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00042-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00043-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00044-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00045-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00046-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00047-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00048-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00049-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00050-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00051-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00052-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00053-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00054-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00055-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 170,
+      "scale_tensors": 170,
+      "shard": "model-00056-of-00057.safetensors",
+      "tensor_bytes": 2139617280
+    },
+    {
+      "preserved": 0,
+      "quantized": 117,
+      "scale_tensors": 117,
+      "shard": "model-00057-of-00057.safetensors",
+      "tensor_bytes": 1472560128
+    },
+    {
+      "preserved": 11,
+      "quantized": 55,
+      "scale_tensors": 55,
+      "shard": "model-00058-of-00070.safetensors",
+      "tensor_bytes": 823871616
+    },
+    {
+      "preserved": 2,
+      "quantized": 55,
+      "scale_tensors": 55,
+      "shard": "model-00059-of-00070.safetensors",
+      "tensor_bytes": 801324032
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00060-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00061-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00062-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00063-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00064-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00065-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00066-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00067-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00068-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 64,
+      "scale_tensors": 64,
+      "shard": "model-00069-of-00070.safetensors",
+      "tensor_bytes": 805502976
+    },
+    {
+      "preserved": 0,
+      "quantized": 28,
+      "scale_tensors": 28,
+      "shard": "model-00070-of-00070.safetensors",
+      "tensor_bytes": 352407552
+    }
+  ],
+  "source": "/root/inference-v2/mini-glm-5.2/v1c-upscale/checkpoints/v1b-mtp-active-decoder-serveddata-align-1k-full-original-dims-tiled-sglang",
+  "weight_map_keys": 20406
+}

model-00004-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b7e70b4b94ebd344d4ae2bec764787fadca75b4fe41588e2d43b678ffba9e9
+size 2140925008

model-00006-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a7bcfed5c7e4e9524272978ed33230f260a16cbab12d42f4eba350ffa5601b
+size 2152327648

model-00007-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bb4c75595284657112df034caff5d2cbcc959117aaac2f90d31fce701b9182
+size 2139659320

model-00009-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f537e2d7e2239cd644a943178fc27f3c93e1b4ecc416b550ff05b135e5c6a29f
+size 2139659656

model-00010-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7b41e64322ed42ba9a539a7b6e7c1fd339dba974e551586448ed86beeb51ab
+size 2139659656

model-00011-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b2b5dfa364441464f23b558eca3565d440cd20ade36763908abab187dce41f
+size 2139659344

model-00013-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e75f7112125141ce680a14bdba19737e0513b11eb2d467d19247dd467bb10a7
+size 2139659656

model-00014-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d596f74f53549f694afcb0987677a65cddfb2fca662e2fc720163bbf7dce36
+size 2139659656

model-00017-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16d4badae257d3d532a23a51a9a7559513d0bd149daf040c8897dc5974cca2d
+size 2139659656

model-00018-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55266867143204d1f551dc708553adf461f1984b4170cbc30b2e5be8a8e67b1
+size 2139659656

model-00019-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23e943e914d0e55ed7dd0de616dec50846ec8f021e70e93a163c9dce1f85e88
+size 2139659512

model-00020-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1596a3c245e26bf4f02936f1c64d8984cc9fbe74a674cc2afc69f269ffe04851
+size 2139659312

model-00023-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8415deee244a8aa3993a4f38a67584611091195c61ecb1ed062c6a159708f658
+size 2139659584

model-00025-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfde038d3ada16f0f8fa34e6a4de090f3680f43cfe1bbb52f71ada8f61626fb
+size 2139659560

model-00026-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e33ba8f3764e2a0fdeb759966375abe6ff78c49d96b5ec0a3e9e2a29694c44
+size 2139659656

model-00029-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697a6d6d76d352cfa41c120e0f5be3459ef4144896b3bb7c43280b38fcd41912
+size 2139659472

model-00031-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee39594f9404d9c23d52c70dbf689bdeed5c981d584ba41cf820dffd4cb50de
+size 2139659656

model-00032-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df84d1bbbd36f772b308cd2dd8fd58bd87b8645eb0df13bde114d410a22bd9e0
+size 2139659408

model-00033-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50490b0de13cf88d7c0062621817b1021eb99c03b588016691888e77dd8f348a
+size 2139659392

model-00035-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f577e8e74ba2d100077e5a5ca541f3a19a3a84a1619201d71902f8783eadae
+size 2139659656

model-00037-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f457602d993e9a7b31f158fe4984d101d709e81e919f0ffbadd77e314c60a7ee
+size 2139659320

model-00038-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29e4b84cf49baf865221b596e4d00bca6243e4ff35cde0b68729be35c288570
+size 2139659656

model-00039-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e0ca533cfaf75f43e617976c5d7602034b2ccd6507b99139d70013fef40583
+size 2139659656

model-00040-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:738f0a843248fef4bcf9a22493c68a0504a8491ecb39193c9cac5c52cef12449
+size 2139659656

model-00041-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526905acbf506151480dc63005459e6b755d4311b6b6446a8836cf799931fdcb
+size 2139659656

model-00042-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fe46fb5cfa3d90c79eb8d8319d34817cebd71684837548fa23cc6fec25e239
+size 2139659912

model-00044-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839ec34b4fb67d65f3dad41040a7bf4f71e114cff2be53d9b3e77eae58a22e27
+size 2139659984

model-00045-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21984805b6992b40e36710875b09c29165f7406534f82c5e5703e6d5088cbaea
+size 2139659656

model-00046-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ed5586a1e5e894b6cd49e269ead882f9d08dceffb3f6b86240b687f47de3d4
+size 2139659840

model-00050-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b90f8826d8275885fe7f32e18d5bf0b99e0e480d9f5c4ac59fefddc629732d9
+size 2139659752

model-00051-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7cee808841079b1287bad24e2fdc524904e7b039c248329e064ca9acc1757c
+size 2139659992

model-00053-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b832ffcb6ee2f044fb02af086bca8a087092a95a6142caf5b2e2f3fedb128da
+size 2139659808

model-00055-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0335c8b51ce8b01a78cb86dcd1f83c3d7ff7a5f1091931164b1168c362c2f29e
+size 2139660000

model-00056-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76ad8e4b5aeacaeb9b92fbefae8ea55dd4bc678c9a121e3ec8c444482552f71
+size 2139659992

model-00057-of-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cd5e0a2f42cc495337be9dcff578642160ab32be870f278bbbb5f53f3b5bb9
+size 1472589448

model-00058-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b356554397bf30b75f49560417fa7e0671b0d7b6040690ec9570d186a48e0dcc
+size 823886416

model-00060-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795a032e1ae0b8a4a452fa879eae47f7a95819163fcbee77bacccc5089285c42
+size 805518808

model-00061-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b572bea52fb12d0a5cd8c59f0512517d122d32c935bca5908e2632eca49566a
+size 805518816

model-00062-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a242fdb6e9888fb837a9cbf17258f0c7700a5afb8a88f06be2496905e45131
+size 805518816

model-00063-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b46657cda9748a50707aadd91cebfaf68280d8503f35d6095c540d37a7b213
+size 805518920

model-00064-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ebd74b63ecad5bbc7941aded0a0d6ff3c466bc2573787f54faaefb9e491a1f
+size 805518944

model-00065-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3618e2637fc74e29eb08a3aac5aa26ae9b52b3212b0f5b059a2fdefdc5590098
+size 805518944

model-00066-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b979fdf14009f6405dedcfb622a603e622ea721ed13d242be02dc9a34b10721
+size 805518936

model-00068-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0d3788a3162aadfd4c2b3b017beaa8f97e88b1f04407be8ae8fd8c4e05d745
+size 805518944

model-00069-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73d3933379d23901b5d8f5532a9cf5c5422b307160b9ef69ded99c95526b667
+size 805518936

model-00070-of-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f837b00c8b13e36dd9840acb5d26e7b724b96a7ee21040a6b606d2647a3fa1
+size 352414504