commit 4a9919af6765009a50e6b82844057c15fe7b8bf4 Author: ModelHub XC Date: Fri Oct 23 13:11:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: JunHowie/Qwen3-14B-Instruct-2512-SFT-NVFP4 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b495fc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..c81af14 --- /dev/null +++ b/README.md @@ -0,0 +1,117 @@ +--- +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE +pipeline_tag: text-generation +base_model: +- Qwen/Qwen3-8B +--- +# Qwen3-14B-Instruct-2512-SFT + +**NOTE：This model is the Instruct-aligned variant, and it will not generate ```` blocks in its outputs. +Additionally, there is no need to specify enable_thinking=False anymore.** + + + +Among them, the 8B and 14B SFT and DFT variants are obtained via full-parameter fine-tuning, while the 32B models are trained using LoRA due to hardware resource constraints.
+The dataset used is the Chinese Distillation Dataset based on Qwen3-235B-2507.available at:[**Chinese-Qwen3-235B-2507-Distill-data-110k**](https://www.modelscope.cn/datasets/swift/Chinese-Qwen3-235B-2507-Distill-data-110k) +
+For details and code regarding model training and quantization, please see[Training and Quantization Guide](https://www.modelscope.cn/learn/3000) +
+Here is the list of models released in this version:
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Model4-bit AWQ8-bit FP8GPTQNVIDIA FP4Weight-Activation
AWQAWQ-asymINT4INT8NVFP4NVFP4-A16W4A16W8A8
Qwen3-8B-Instruct-2512-DFTAWQawq-asymFP8GPTQ(int4)GPTQ(int8)NVFP4NVFP4A16W4A16W8A8
Qwen3-8B-Instruct-2512-SFTAWQawq-asymFP8GPTQ(int4)GPTQ(int8)NVFP4NVFP4A16W4A16W8A8
Qwen3-14B-Instruct-2512-DFTAWQawq-asymFP8GPTQ(int4)GPTQ(int8)NVFP4NVFP4A16W4A16W8A8
Qwen3-14B-Instruct-2512-SFTAWQawq-asymFP8GPTQ(int4)GPTQ(int8)NVFP4NVFP4A16W4A16W8A8
Qwen3-32B-Instruct-2512-DFTAWQawq-asymFP8GPTQ(int4)GPTQ(int8)NVFP4NVFP4A16W4A16W8A8
+ + + +### 【Dependencies】 +``` +vllm>=0.10.2 +transformers>=4.56.1 +``` + + + diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..699ff8d --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,85 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set content = message.content %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is defined and message.reasoning_content is not none %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in message.content %} + {%- set content = message.content.split('')[-1].lstrip('\n') %} + {%- set reasoning_content = message.content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..351efb1 --- /dev/null +++ b/config.json @@ -0,0 +1,118 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 17408, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 40, + "model_type": "qwen3", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "quantization_config": { + "config_groups": { + "group_0": { + "format": "nvfp4-pack-quantized", + "input_activations": { + "actorder": null, + "block_structure": null, + "dynamic": "local", + "group_size": 16, + "num_bits": 4, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "tensor_group", + "symmetric": true, + "type": "float" + }, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": 16, + "num_bits": 4, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "tensor_group", + "symmetric": true, + "type": "float" + } + } + }, + "format": "nvfp4-pack-quantized", + "global_compression_ratio": null, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": {}, + "transform_config": {}, + "version": "0.12.2" + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.56.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..078fb41 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.56.2" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..4af624e --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f5a067a6adb58bec30d71589aca49d49dd71be3919e50139e9c649f54a25f7 +size 4986098936 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..0176e86 --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48bc31ef00054e4e0f006637e8d5f978e3a1e78968e97d7a95736b8467e67df4 +size 4002505744 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..54e4529 --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87ba7049f2e8b016c577d7e1ff053d6e74cf2b27360cf46e7e628a76552c9f44 +size 1555824768 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b7c6d8d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1291 @@ +{ + "metadata": { + "total_parameters": 8988032560, + "total_size": 10544283840 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.input_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.weight_global_scale": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.weight_packed": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.input_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight_global_scale": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00002-of-00003.safetensors" + } +} diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..c3664c0 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,6 @@ +default_stage: + default_modifiers: + QuantizationModifier: + targets: [Linear] + ignore: [lm_head] + scheme: NVFP4 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ddaf698 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833