commit 432a28858cbc8767dd90e5f7fa42baf7f947a4e2 Author: ModelHub XC Date: Sat Jun 13 05:52:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..df82948 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.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 + +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +bannerQwenV4-4bit.png 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..070a0d2 --- /dev/null +++ b/README.md @@ -0,0 +1,175 @@ +--- +language: +- en +- zh +- vi +- id +- th +- fil +- ta +- ms +- km +- lo +- my +base_model: +- aisingapore/Qwen-SEA-LION-v4-32B-IT +new_version: aisingapore/Qwen-SEA-LION-v4.5-27B-IT +base_model_relation: quantized +library_name: transformers +pipeline_tag: text-generation +license: mit +--- +![Banner!](bannerQwenV4-4bit.png "v4-banner-Qwen-instruct") + +## Qwen-SEA-LION-v4-32B-IT-4BIT (GPTQ model) + +Last update: 2025-10-17 + +SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region. + +As of 17 Oct 2025, Qwen-SEA-LION-v4-32B-IT excels at Southeast Asian (SEA) tasks when compared to other open models with fewer than 200 billion parameters and demonstrates performance comparable to that of larger and top closed models. Qwen-SEA-LION-v4-32B-IT was quantized to create *Qwen-SEA-LION-v4-32B-IT-4BIT*. The quantized version has little degradation (<0.3% on average) in performance compared to Qwen-SEA-LION-v4-32B-IT (for detailed rankings, please refer to the [leaderboard](https://leaderboard.sea-lion.ai/)), and Qwen-SEA-LION-v4-32B-IT-4BIT version can run on a laptop. + +Qwen-SEA-LION-v4-32B-IT inherits the following features from Qwen3-32B: + +- 32,768 of context length natively + +## Model Details + +### Model Description + +SEA-LION stands for *Southeast Asian Languages In One Network*. + +Quantization was performed on Qwen-SEA-LION-v4-32B-IT to produce optimized variants that reduce memory requirements while maintaining model quality. These quantized models support inference on a range of consumer-grade GPUs and are compatible with various inference engines. + +For tokenization, the model employs the default tokenizer used in Qwen3-32B. + +- **Developed by:** AI Products Pillar, AI Singapore +- **Funded by:** Singapore NRF +- **Shared by:** AI Products Pillar, AI Singapore +- **Model type:** Decoder +- **Context Length:** 32k tokens +- **Language(s) (NLP):** Burmese, English, Indonesian, Khmer, Lao, Malay, Mandarin, Tagalog, Tamil, Thai, and Vietnamese +- **License:** [MIT](https://mit-license.org/) +- **Continue pretrained from model:** [Qwen-3-32B](https://huggingface.co/Qwen/Qwen3-32B) + +## Uses + +### Available Quantized Versions + +- [Qwen-SEA-LION-v4-32B-IT](https://huggingface.co/aisingapore/Qwen-SEA-LION-v4-32B-IT) +- [Qwen-SEA-LION-v4-32B-IT-4BIT](https://huggingface.co/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT) +- [Qwen-SEA-LION-v4-32B-IT-8BIT](https://huggingface.co/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT) + +### Out-of-Scope Use + +The model has *not* been aligned for safety. Developers and users should perform their own safety fine-tuning and related security measures. In no event shall the authors be held liable for any claims, damages, or other liabilities arising from the use of the released weights and codes. + +## Bias, Risks, and Limitations + +### Caveats || Risks + +*The model was not tested for robustness against adversarial prompting.* It is important for users to be aware that our model exhibits certain limitations that warrant consideration. Like many LLMs, the model can hallucinate and occasionally generates irrelevant content, introducing fictional elements that are not grounded in the provided context. Users should also exercise caution in interpreting and validating the model's responses due to the potential inconsistencies. + +## Limitations + +In terms of vision capability, Qwen-SEA-LION-v4-32B-IT has been trained and fine-tuned exclusively on the text back-end. As a result, its vision capabilities are expected to be comparable to those of Qwen3 32B and may not exhibit significant improvements or differences in this area. () + +## How to Get Started with the Model + +Use the code below to get started with the model using the 🤗 Transformers library. +> The model defaults to non-thinking mode. To enable thinking mode, please use `enable_thinking=True`. +> +> + + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT" + +# load the tokenizer and the model +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) + +# prepare the model input +prompt = "Give me a short introduction to large language model." +messages = [ + {"role": "user", "content": prompt} +] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, + enable_thinking=True # Switches between thinking and non-thinking modes. Default is True. +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +# conduct text completion +generated_ids = model.generate( + **model_inputs, + max_new_tokens=32768 +) +output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() + +# parsing thinking content +try: + # rindex finding 151668 () + index = len(output_ids) - output_ids[::-1].index(151668) +except ValueError: + index = 0 + +thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n") +content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n") + +print("thinking content:", thinking_content) +print("content:", content) +``` +## Training Details + +### Training Data + +The dataset comprises Burmese, Indonesian, Malay, Tagalog, Tamil, Thai and Vietnamese languages, collected from a mixture of sources including web data, code, open-source datasets, and synthetically generated datasets, amounting to a total of 100 billion tokens sampled. + +## Evaluation + +### Model Performance + +![LeaderboardResults!](sea-helm_scores_17_oct_02pm_wGPTQ.png "LeaderboardCaptured17Oct2pmWGPTQ") + +For details on Qwen-SEA-LION-v4-32B-IT performance, please refer to the SEA-HELM leaderboard, . + +### Resource Metrics + +| Quantized Variant | Num. Parameters | Storage Size (GB) | VRAM Required (GB) | Time to First Token (s) | Tokens per Second | +| --- | --- | --- | --- | --- | --- | +| BF16 | 32B | 65.57 | 61.03 | 2.20 | 52.98 | +| 8-bit (GPTQ) | 32B | 34.34 | 32.04 | 0.35 | 68.85 | +| 4-bit (GPTQ) | 32B | 19.93 | 19.43 | 0.34 | 78.20 | + +*Additional Remarks:* + +- TTFT and Tokens per Sec: measured with vLLM on localhost and concurrency = 1. +- Reported results are the median (p50) values, calculated across 10 requests. +- Model size taken from vLLM upon loading +- Input size 4K, output 1K +- Tests conducted on a system with an NVIDIA H200 GPU +- For more details on the quantized model, please refer to [config.json](https://huggingface.co/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT/blob/main/config.json) + +## More Information + +This is the repository for the commercial instruction-tuned model. The model has *not* been aligned for safety. Developers and users should perform their own safety fine-tuning and related security measures. In no event shall the authors be held liable for any claims, damages, or other liabilities arising from the use of the released weights and codes. + +For more info, please contact us using this [sealion@aisingapore.org](mailto:sealion@aisingapore.org) + +## Acknowledgement + +This project is supported by the National Research Foundation Singapore and Infocomm Media Development Authority (IMDA), +Singapore under its National Large Language Model Funding Initiative. + +## Team + +Ahn Jeongmi, Antonyrex Sajeban, Chan Hok Teng Adwin, Cheng Zi Yi Nicholas, Choa Hsueh Mei Esther, Heng Jonathan, Huang Yuli, Hulagadri Adithya Venkatadri, Jann Railey Estrada Montalan, Lau Wayne, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Limkonchotiwat Peerat, Muhammad Ridzuan Bin Mokhtar, Nagarajan Karthik, Ng Boon Cheong Raymond, Ngee Chia Tai, Ngui Jian Gang, Nguyen Thanh Ngan, Ong Jin Jie Brandon, Ong Tat-Wee David, Ong Zhi Hao, Pereira Mark, Rengarajan Hamsawardhini, Siow Wei Kang Bryan, Susanto Yosephine, Sutaveephamochanon Anocha, Tan Choon Meng, Tan Chor Phin Evelyn, Tan Siao Wei Jessica, Tan Yixian, Tee Jun Yun, Teng Kok Wai Walter, Teo Eng Sipp Leslie, Tjhi William, Yeo Yeow Tong, Yong Xianbin, Zhang Zhou, Liew Rachel, Liu Bing Jie Darius, Tep Kilian Rithi (GoTo) \ No newline at end of file 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/bannerQwenV4-4bit.png b/bannerQwenV4-4bit.png new file mode 100644 index 0000000..5c50147 --- /dev/null +++ b/bannerQwenV4-4bit.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6467bb170092725d238b498b3f6bc8896879a59f7762b4653a7373e4e1ea3bfc +size 1862135 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..dd26387 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- 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 message.content is string 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.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.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' }} + {{- 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 not defined or 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..2b2dd51 --- /dev/null +++ b/config.json @@ -0,0 +1,131 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 25600, + "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", + "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": 64, + "model_type": "qwen3", + "num_attention_heads": 64, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "quantization_config": { + "config_groups": { + "group_0": { + "format": "pack-quantized", + "input_activations": null, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": "static", + "block_structure": null, + "dynamic": false, + "group_size": 64, + "num_bits": 4, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "group", + "symmetric": false, + "type": "int" + } + } + }, + "format": "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, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.2", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..383cf5a --- /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": "4.55.2" +} 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-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..f583a0b --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55dc04a17317bacac82444277fa0eb62b5814d68567cb6249325a542df3403f +size 4998508560 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..c969da6 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392632e2982a8f579f037a2ae6f9ea74a0a612d05a074fa552bae9b6a02ec115 +size 4997264576 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..044e580 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5814c55660935e1e35cae22ac98bcc7567cbe6c51a7d6d3509bb23ab05dd500c +size 4994437856 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..ca8320b --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af57b188006e2a64e6cc1d79e4cba1513778ea0c5581af85f8945a7ac33902a9 +size 4944817968 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b1665c5 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,2059 @@ +{ + "metadata": { + "total_parameters": 6005741440, + "total_size": 19934790656 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight_packed": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight_shape": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight_zero_point": "model-00002-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.51.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.51.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.weight_packed": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.weight_shape": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.weight_zero_point": "model-00003-of-00004.safetensors", + "model.layers.52.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.weight_packed": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.weight_shape": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.weight_zero_point": "model-00004-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight_zero_point": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..085402f --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,27 @@ +quant_stage: + quant_modifiers: + GPTQModifier: + config_groups: + group_0: + targets: [Linear] + weights: + num_bits: 4 + type: int + symmetric: false + group_size: 64 + strategy: group + block_structure: null + dynamic: false + actorder: !!python/object/apply:compressed_tensors.quantization.quant_args.ActivationOrdering [ + static] + observer: minmax + observer_kwargs: {} + input_activations: null + output_activations: null + format: null + targets: [Linear] + ignore: [lm_head, 're:.*q_norm', 're:.*k_norm'] + block_size: 128 + dampening_frac: 0.01 + actorder: static + offload_hessians: false diff --git a/sea-helm_scores_17_oct_02pm_wGPTQ.png b/sea-helm_scores_17_oct_02pm_wGPTQ.png new file mode 100644 index 0000000..23411dc Binary files /dev/null and b/sea-helm_scores_17_oct_02pm_wGPTQ.png differ 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