commit eecc5a6c2d2d08ac5306b5da9b9f43db8ffc437f Author: ModelHub XC Date: Wed Oct 21 02:34:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: QuantTrio/KAT-Dev-GPTQ-Int4 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8abc1aa --- /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 + +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json 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..6dea0b3 --- /dev/null +++ b/README.md @@ -0,0 +1,158 @@ +--- +language: + - multilingual +license: apache-2.0 +license_name: kwaipilot-license +license_link: LICENSE +library_name: transformers +pipeline_tag: text-generation +tags: +- GPTQ +- Int4 +- vLLM +base_model: + - Kwaipilot/KAT-Dev +base_model_relation: quantized +--- +# KAT-Dev-GPTQ-Int4 +Base model: [Kwaipilot/KAT-Dev](https://huggingface.co/Kwaipilot/KAT-Dev) + +Calibrate using the https://huggingface.co/datasets/timdettmers/openassistant-guanaco/blob/main/openassistant_best_replies_eval.jsonl dataset. +
+The quantization configuration is as follows + +``` +quant_config = QuantizeConfig(bits=4, group_size=128, desc_act=False) +``` + +### 【vLLM Startup Command】 +``` +vllm serve JunHowie/KAT-Dev-GPTQ-Int4 +``` + +### 【Dependencies】 +``` +vllm>=0.10.2 +transformers>=4.56.1 +``` + +### 【Model Download】 + +```python +from huggingface_hub import snapshot_download +snapshot_download('JunHowie/KAT-Dev-GPTQ-Int4', cache_dir="your_local_path") +``` + +### 【Overview】 +
+ Kwaipilot +
+ +
+ + +# News + +🔥 We’re thrilled to announce the release of KAT-Dev-72B-Exp, our latest and most powerful model yet! + +🔥 You can now try our **strongest** proprietary coder model **KAT-Coder** directly on the [StreamLake](https://www.streamlake.ai/product/kat-coder) platform **for free**. + +# Highlights +**KAT-Dev-32B** is an open-source 32B-parameter model for software engineering tasks. + +On SWE-Bench Verified, **KAT-Dev-32B** achieves comparable performance with **62.4%** resolved and ranks **5th** among all open-source models with different scales. + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/61ee40a269351366e29972ad/dTpQQPQnp1TdD4YB8gZAu.png) + +# Introduction + +**KAT-Dev-32B** is optimized via several stages of training, including a mid-training stage, supervised fine-tuning (SFT) & reinforcement fine-tuning (RFT) stage and an large-scale agentic reinforcement learning (RL) stage. In summary, our contributions include: + + + + + + + + + + + + + + + + + + + + + + +
StageKey Techniques
1. Mid-TrainingWe observe that adding extensive training for tool-use capability, multi-turn interaction, and instruction-following at this stage may not yield large performance gains in the current results (e.g., on leaderboards like SWE-bench). However, since our experiments are based on the Qwen3-32B model, we find that enhancing these foundational capabilities will have a significant impact on the subsequent SFT and RL stages. This suggests that improving such core abilities can profoundly influence the model’s capacity to handle more complex tasks. +
2. SFT & RFTWe meticulously curated eight task types and eight programming scenarios during the SFT stage to ensure the model’s generalization and comprehensive capabilities. Moreover, before RL, we innovatively introduced an RFT stage. Compared with traditional RL, we incorporate “teacher trajectories” annotated by human engineers as guidance during training—much like a learner driver being assisted by an experienced co-driver before officially driving after getting a license. This step not only boosts model performance but also further stabilizes the subsequent RL training. +
3. Agentic RL ScalingScaling agentic RL hinges on three challenges: efficient learning over nonlinear trajectory histories, leveraging intrinsic model signals, and building scalable high-throughput infrastructure. We address these with a multi-level prefix caching mechanism in the RL training engine, an entropy-based trajectory pruning technique, and an inner implementation of SeamlessFlow[1] architecture that cleanly decouples agents from training while exploiting heterogeneous compute. These innovations together cut scaling costs and enable efficient large-scale RL. +
+ +For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://kwaipilot.github.io/KAT-Coder/). + +# Quickstart + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "Kwaipilot/KAT-Dev" + +# 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, +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +# conduct text completion +generated_ids = model.generate( + **model_inputs, + max_new_tokens=65536 +) +output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() + +content = tokenizer.decode(output_ids, skip_special_tokens=True) + +print("content:", content) +``` + +## Claude Code + ### vllm server +``` +MODEL_PATH="Kwaipilot/KAT-Dev" + +vllm serve $MODEL_PATH \ + --enable-prefix-caching \ + --tensor-parallel-size 8 \ + --tool-parser-plugin $MODEL_PATH/qwen3coder_tool_parser.py \ + --chat-template $MODEL_PATH/chat_template.jinja \ + --enable-auto-tool-choice --tool-call-parser qwen3_coder +``` + +[claude-code-router](https://github.com/musistudio/claude-code-router) is a third-party routing utility that allows Claude Code to flexibly switch between different backend APIs. +On the dashScope platform, you can install the **claude-code-config** extension package, which automatically generates a default configuration for `claude-code-router` with built-in dashScope support. + +Once the configuration files and plugin directory are generated, the environment required by `ccr` will be ready. +If needed, you can still manually edit `~/.claude-code-router/config.json` and the files under `~/.claude-code-router/plugins/` to customize the setup. + +Finally, simply start `ccr` to run Claude Code and seamlessly connect it with the powerful coding capabilities of **KAT-Dev-32B**. +Happy coding! diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..6d7cb69 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,117 @@ +{% macro render_extra_keys(json_dict, handled_keys) %} + {%- if json_dict is mapping %} + {%- for json_key in json_dict if json_key not in handled_keys %} + {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %} + {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '' }} + {%- else %} + {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '' }} + {%- endif %} + {%- endfor %} + {%- endif %} +{% endmacro %} + +{%- if messages[0]["role"] == "system" %} + {%- set system_message = messages[0]["content"] %} + {%- set loop_messages = messages[1:] %} +{%- else %} + {%- set loop_messages = messages %} +{%- endif %} + +{%- if not tools is defined %} + {%- set tools = [] %} +{%- endif %} + +{%- if system_message is defined %} + {{- "<|im_start|>system\n" + system_message }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- "<|im_start|>system\nYou are a helpful AI assistant that can interact with a computer to solve tasks." }} + {%- endif %} +{%- endif %} +{%- if tools is iterable and tools | length > 0 %} + {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }} + {{- "" }} + {%- for tool in tools %} + {%- if tool.function is defined %} + {%- set tool = tool.function %} + {%- endif %} + {{- "\n\n" ~ tool.name ~ "" }} + {%- if tool.description is defined %} + {{- '\n' ~ (tool.description | trim) ~ '' }} + {%- endif %} + {{- '\n' }} + {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %} + {%- for param_name, param_fields in tool.parameters.properties|items %} + {{- '\n' }} + {{- '\n' ~ param_name ~ '' }} + {%- if param_fields.type is defined %} + {{- '\n' ~ (param_fields.type | string) ~ '' }} + {%- endif %} + {%- if param_fields.description is defined %} + {{- '\n' ~ (param_fields.description | trim) ~ '' }} + {%- endif %} + {%- set handled_keys = ['name', 'type', 'description'] %} + {{- render_extra_keys(param_fields, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {% set handled_keys = ['type', 'properties'] %} + {{- render_extra_keys(tool.parameters, handled_keys) }} + {{- '\n' }} + {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %} + {{- render_extra_keys(tool, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} +{%- endif %} +{%- if system_message is defined %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in loop_messages %} + {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %} + {{- '<|im_start|>' + message.role }} + {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %} + {{- '\n' + message.content | trim + '\n' }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n\n' }} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user\n' }} + {%- endif %} + {{- '\n' }} + {{- message.content }} + {{- '\n\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..68f9e87 --- /dev/null +++ b/config.json @@ -0,0 +1,120 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 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": 131072, + "max_window_layers": 64, + "model_type": "qwen3", + "num_attention_heads": 64, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "quantization_config": { + "bits": 4, + "checkpoint_format": "gptq", + "desc_act": false, + "group_size": 128, + "lm_head": false, + "meta": { + "act_group_aware": false, + "damp_auto_increment": 0.01, + "damp_percent": 0.05, + "mse": 0.0, + "quantizer": [ + "gptqmodel:4.2.5" + ], + "static_groups": false, + "true_sequential": true, + "uri": "https://github.com/modelcloud/gptqmodel", + "v2": false, + "v2_alpha": 0.25 + }, + "pack_dtype": "int32", + "quant_method": "gptq", + "sym": true + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.56.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} 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..078fb41 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.56.2" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..642046e --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3ce822b5879263d052dd03fa1eff2f07a60f3ea83b8869936d110e7e5c21f8 +size 3955280848 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..8b2c063 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a423076e328bbfb7ec6ac84e10a63a868637ab4c8b6d4037e4428b970b572f +size 3989151776 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..ec2ca4e --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f996f378c1b5382a28a914a25fa2889f49aafdd582d6c1a8994811f61ee51d9 +size 3939923288 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..50b8c17 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7221ada0047e6151d3e31af16af04a58f66a85214c48b9a6fd689f65305e9bb +size 3989151824 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..763ef8d --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2391b141b28b8201111096b54bac87a47c45cfded1379deacf8e6073e126b3 +size 3467226552 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..94359fb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,2058 @@ +{ + "metadata": { + "total_size": 19340503040 + }, + "weight_map": { + "lm_head.weight": "model-00005-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.g_idx": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.qweight": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.qzeros": "model-00003-of-00005.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00005.safetensors", + "model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.50.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.down_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.mlp.up_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.56.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.gate_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.56.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.56.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00004-of-00005.safetensors", + "model.layers.57.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.60.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.down_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.gate_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.mlp.up_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.g_idx": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.qweight": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.qzeros": "model-00005-of-00005.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00005-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.9.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00002-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00005.safetensors", + "model.norm.weight": "model-00005-of-00005.safetensors" + } +} diff --git a/quant_log.csv b/quant_log.csv new file mode 100644 index 0000000..6b3eaa2 --- /dev/null +++ b/quant_log.csv @@ -0,0 +1,449 @@ +layer,module,loss,samples,damp,time +0,self_attn.k_proj,0.0000000162,0.05000,3.234 +0,self_attn.v_proj,0.0000000127,0.05000,1.044 +0,self_attn.q_proj,0.0000000816,0.05000,1.081 +0,self_attn.o_proj,0.0000004007,0.05000,1.772 +0,mlp.gate_proj,0.0000024797,0.05000,1.139 +0,mlp.up_proj,0.0000021738,0.05000,1.122 +0,mlp.down_proj,0.0000023848,0.05000,8.001 +1,self_attn.k_proj,0.0000000269,0.05000,1.034 +1,self_attn.v_proj,0.0000000269,0.05000,1.033 +1,self_attn.q_proj,0.0000001541,0.05000,1.057 +1,self_attn.o_proj,0.0000002456,0.05000,2.065 +1,mlp.gate_proj,0.0001649253,0.05000,1.130 +1,mlp.up_proj,0.0000509813,0.05000,1.139 +1,mlp.down_proj,0.0000078315,0.05000,8.037 +2,self_attn.k_proj,0.0000000458,0.05000,1.044 +2,self_attn.v_proj,0.0000000446,0.05000,1.042 +2,self_attn.q_proj,0.0000002448,0.05000,1.073 +2,self_attn.o_proj,0.0000004594,0.05000,1.767 +2,mlp.gate_proj,0.0002349929,0.05000,1.133 +2,mlp.up_proj,0.0000981800,0.05000,1.123 +2,mlp.down_proj,0.0000073423,0.05000,8.280 +3,self_attn.k_proj,0.0000000833,0.05000,1.046 +3,self_attn.v_proj,0.0000000865,0.05000,1.036 +3,self_attn.q_proj,0.0000004506,0.05000,1.061 +3,self_attn.o_proj,0.0000004512,0.05000,1.760 +3,mlp.gate_proj,0.0003456217,0.05000,1.165 +3,mlp.up_proj,0.0001514415,0.05000,1.139 +3,mlp.down_proj,0.0000142816,0.05000,8.122 +4,self_attn.k_proj,0.0000001313,0.05000,1.087 +4,self_attn.v_proj,0.0000001358,0.05000,1.077 +4,self_attn.q_proj,0.0000007362,0.05000,1.086 +4,self_attn.o_proj,0.0000006806,0.05000,1.787 +4,mlp.gate_proj,0.0004579198,0.05000,1.393 +4,mlp.up_proj,0.0002564290,0.05000,1.235 +4,mlp.down_proj,0.0000159178,0.05000,8.022 +5,self_attn.k_proj,0.0000001601,0.05000,1.057 +5,self_attn.v_proj,0.0000001558,0.05000,1.053 +5,self_attn.q_proj,0.0000008758,0.05000,1.111 +5,self_attn.o_proj,0.0000006760,0.05000,1.793 +5,mlp.gate_proj,0.0005507642,0.05000,1.163 +5,mlp.up_proj,0.0002391874,0.05000,1.142 +5,mlp.down_proj,0.0000223429,0.05000,7.979 +6,self_attn.k_proj,0.0000001918,0.05000,1.062 +6,self_attn.v_proj,0.0000002022,0.05000,1.049 +6,self_attn.q_proj,0.0000011141,0.05000,1.076 +6,self_attn.o_proj,0.0000007390,0.05000,1.766 +6,mlp.gate_proj,0.0009107982,0.05000,1.126 +6,mlp.up_proj,0.0005256533,0.05000,1.121 +6,mlp.down_proj,0.0043096024,0.05000,7.967 +7,self_attn.k_proj,0.0000011770,0.05000,1.037 +7,self_attn.v_proj,0.0000012232,0.05000,1.034 +7,self_attn.q_proj,0.0000069287,0.05000,1.058 +7,self_attn.o_proj,0.0000025039,0.05000,1.751 +7,mlp.gate_proj,0.0009953627,0.05000,1.117 +7,mlp.up_proj,0.0005493904,0.05000,1.125 +7,mlp.down_proj,0.0000297612,0.05000,7.977 +8,self_attn.k_proj,0.0000010946,0.05000,1.069 +8,self_attn.v_proj,0.0000011919,0.05000,1.056 +8,self_attn.q_proj,0.0000061875,0.05000,1.069 +8,self_attn.o_proj,0.0000025796,0.05000,1.768 +8,mlp.gate_proj,0.0002623779,0.05000,1.124 +8,mlp.up_proj,0.0001344016,0.05000,1.116 +8,mlp.down_proj,0.0000189611,0.05000,7.998 +9,self_attn.k_proj,0.0000006171,0.05000,1.059 +9,self_attn.v_proj,0.0000006324,0.05000,1.072 +9,self_attn.q_proj,0.0000033820,0.05000,1.084 +9,self_attn.o_proj,0.0000015995,0.05000,1.779 +9,mlp.gate_proj,0.0001099972,0.05000,1.142 +9,mlp.up_proj,0.0001023062,0.05000,1.150 +9,mlp.down_proj,0.0000218911,0.05000,7.992 +10,self_attn.k_proj,0.0000009853,0.05000,1.044 +10,self_attn.v_proj,0.0000011111,0.05000,1.036 +10,self_attn.q_proj,0.0000058205,0.05000,1.061 +10,self_attn.o_proj,0.0000031338,0.05000,1.750 +10,mlp.gate_proj,0.0001112629,0.05000,1.220 +10,mlp.up_proj,0.0001056672,0.05000,1.115 +10,mlp.down_proj,0.0000184607,0.05000,8.407 +11,self_attn.k_proj,0.0000013373,0.05000,1.040 +11,self_attn.v_proj,0.0000014252,0.05000,1.057 +11,self_attn.q_proj,0.0000076782,0.05000,1.102 +11,self_attn.o_proj,0.0000045550,0.05000,1.756 +11,mlp.gate_proj,0.0001260963,0.05000,1.126 +11,mlp.up_proj,0.0001195048,0.05000,1.119 +11,mlp.down_proj,0.0000218171,0.05000,8.003 +12,self_attn.k_proj,0.0000009299,0.05000,1.044 +12,self_attn.v_proj,0.0000010058,0.05000,1.041 +12,self_attn.q_proj,0.0000054316,0.05000,1.077 +12,self_attn.o_proj,0.0000024059,0.05000,1.766 +12,mlp.gate_proj,0.0001412866,0.05000,1.116 +12,mlp.up_proj,0.0001323689,0.05000,1.117 +12,mlp.down_proj,0.0000244210,0.05000,7.955 +13,self_attn.k_proj,0.0000017760,0.05000,1.062 +13,self_attn.v_proj,0.0000018995,0.05000,1.051 +13,self_attn.q_proj,0.0000102478,0.05000,1.079 +13,self_attn.o_proj,0.0000036599,0.05000,1.810 +13,mlp.gate_proj,0.0001465452,0.05000,1.188 +13,mlp.up_proj,0.0001332961,0.05000,1.174 +13,mlp.down_proj,0.0000243287,0.05000,8.004 +14,self_attn.k_proj,0.0000009200,0.05000,1.052 +14,self_attn.v_proj,0.0000009821,0.05000,1.049 +14,self_attn.q_proj,0.0000048295,0.05000,1.076 +14,self_attn.o_proj,0.0000034132,0.05000,1.790 +14,mlp.gate_proj,0.0001352126,0.05000,1.166 +14,mlp.up_proj,0.0001249658,0.05000,1.125 +14,mlp.down_proj,0.0000223208,0.05000,8.035 +15,self_attn.k_proj,0.0000008635,0.05000,1.041 +15,self_attn.v_proj,0.0000009282,0.05000,1.048 +15,self_attn.q_proj,0.0000051504,0.05000,1.069 +15,self_attn.o_proj,0.0000034768,0.05000,1.808 +15,mlp.gate_proj,0.0001202492,0.05000,1.134 +15,mlp.up_proj,0.0001143246,0.05000,1.126 +15,mlp.down_proj,0.0000198175,0.05000,7.997 +16,self_attn.k_proj,0.0000008311,0.05000,1.044 +16,self_attn.v_proj,0.0000009154,0.05000,1.044 +16,self_attn.q_proj,0.0000048815,0.05000,1.071 +16,self_attn.o_proj,0.0000034149,0.05000,1.769 +16,mlp.gate_proj,0.0001051558,0.05000,1.122 +16,mlp.up_proj,0.0001000832,0.05000,1.120 +16,mlp.down_proj,0.0000178747,0.05000,7.986 +17,self_attn.k_proj,0.0000008668,0.05000,1.065 +17,self_attn.v_proj,0.0000008656,0.05000,1.034 +17,self_attn.q_proj,0.0000049575,0.05000,1.060 +17,self_attn.o_proj,0.0000033593,0.05000,1.801 +17,mlp.gate_proj,0.0001086903,0.05000,1.307 +17,mlp.up_proj,0.0001033014,0.05000,1.149 +17,mlp.down_proj,0.0000185236,0.05000,8.088 +18,self_attn.k_proj,0.0000011330,0.05000,1.038 +18,self_attn.v_proj,0.0000011757,0.05000,1.035 +18,self_attn.q_proj,0.0000066043,0.05000,1.060 +18,self_attn.o_proj,0.0000032982,0.05000,1.778 +18,mlp.gate_proj,0.0001154338,0.05000,1.132 +18,mlp.up_proj,0.0001092103,0.05000,1.119 +18,mlp.down_proj,0.0000206254,0.05000,8.189 +19,self_attn.k_proj,0.0000012775,0.05000,1.064 +19,self_attn.v_proj,0.0000013057,0.05000,1.055 +19,self_attn.q_proj,0.0000077177,0.05000,1.096 +19,self_attn.o_proj,0.0000044452,0.05000,1.800 +19,mlp.gate_proj,0.0001260705,0.05000,1.486 +19,mlp.up_proj,0.0001200554,0.05000,1.139 +19,mlp.down_proj,0.0000240489,0.05000,8.030 +20,self_attn.k_proj,0.0000021487,0.05000,1.063 +20,self_attn.v_proj,0.0000023166,0.05000,1.042 +20,self_attn.q_proj,0.0000125007,0.05000,1.071 +20,self_attn.o_proj,0.0000046935,0.05000,1.767 +20,mlp.gate_proj,0.0001376763,0.05000,1.140 +20,mlp.up_proj,0.0001314726,0.05000,1.122 +20,mlp.down_proj,0.0000271172,0.05000,7.966 +21,self_attn.k_proj,0.0000024297,0.05000,1.054 +21,self_attn.v_proj,0.0000025375,0.05000,1.049 +21,self_attn.q_proj,0.0000141194,0.05000,1.082 +21,self_attn.o_proj,0.0000085868,0.05000,1.793 +21,mlp.gate_proj,0.0001451987,0.05000,1.146 +21,mlp.up_proj,0.0001385588,0.05000,1.146 +21,mlp.down_proj,0.0000308469,0.05000,8.023 +22,self_attn.k_proj,0.0000021045,0.05000,1.048 +22,self_attn.v_proj,0.0000022902,0.05000,1.063 +22,self_attn.q_proj,0.0000127400,0.05000,1.062 +22,self_attn.o_proj,0.0000103736,0.05000,1.779 +22,mlp.gate_proj,0.0001592715,0.05000,1.118 +22,mlp.up_proj,0.0001518224,0.05000,1.117 +22,mlp.down_proj,0.0000371563,0.05000,7.971 +23,self_attn.k_proj,0.0000029360,0.05000,1.048 +23,self_attn.v_proj,0.0000033406,0.05000,1.038 +23,self_attn.q_proj,0.0000168955,0.05000,1.065 +23,self_attn.o_proj,0.0000069991,0.05000,1.822 +23,mlp.gate_proj,0.0001751471,0.05000,1.119 +23,mlp.up_proj,0.0001665793,0.05000,1.115 +23,mlp.down_proj,0.0000446570,0.05000,7.956 +24,self_attn.k_proj,0.0000052270,0.05000,1.056 +24,self_attn.v_proj,0.0000058457,0.05000,1.063 +24,self_attn.q_proj,0.0000323477,0.05000,1.082 +24,self_attn.o_proj,0.0000152148,0.05000,1.768 +24,mlp.gate_proj,0.0001969212,0.05000,1.136 +24,mlp.up_proj,0.0001863398,0.05000,1.122 +24,mlp.down_proj,0.0000521306,0.05000,8.003 +25,self_attn.k_proj,0.0000045368,0.05000,1.051 +25,self_attn.v_proj,0.0000049879,0.05000,1.045 +25,self_attn.q_proj,0.0000270423,0.05000,1.071 +25,self_attn.o_proj,0.0000139668,0.05000,1.761 +25,mlp.gate_proj,0.0002213674,0.05000,1.138 +25,mlp.up_proj,0.0002081905,0.05000,1.123 +25,mlp.down_proj,0.0000665647,0.05000,8.044 +26,self_attn.k_proj,0.0000041029,0.05000,1.053 +26,self_attn.v_proj,0.0000047737,0.05000,1.059 +26,self_attn.q_proj,0.0000243842,0.05000,1.070 +26,self_attn.o_proj,0.0000125715,0.05000,1.760 +26,mlp.gate_proj,0.0002470852,0.05000,1.130 +26,mlp.up_proj,0.0002283383,0.05000,1.125 +26,mlp.down_proj,0.0000837923,0.05000,8.451 +27,self_attn.k_proj,0.0000060690,0.05000,1.064 +27,self_attn.v_proj,0.0000072178,0.05000,1.058 +27,self_attn.q_proj,0.0000348095,0.05000,1.088 +27,self_attn.o_proj,0.0000136795,0.05000,1.776 +27,mlp.gate_proj,0.0002878364,0.05000,1.129 +27,mlp.up_proj,0.0002608704,0.05000,1.129 +27,mlp.down_proj,0.0001052239,0.05000,8.030 +28,self_attn.k_proj,0.0000077865,0.05000,1.051 +28,self_attn.v_proj,0.0000093256,0.05000,1.052 +28,self_attn.q_proj,0.0000463542,0.05000,1.075 +28,self_attn.o_proj,0.0000149359,0.05000,1.786 +28,mlp.gate_proj,0.0003251187,0.05000,1.134 +28,mlp.up_proj,0.0002960902,0.05000,1.120 +28,mlp.down_proj,0.0001167624,0.05000,7.985 +29,self_attn.k_proj,0.0000116028,0.05000,1.046 +29,self_attn.v_proj,0.0000124041,0.05000,1.043 +29,self_attn.q_proj,0.0000637293,0.05000,1.073 +29,self_attn.o_proj,0.0000136918,0.05000,1.772 +29,mlp.gate_proj,0.0003617665,0.05000,1.127 +29,mlp.up_proj,0.0003126921,0.05000,1.123 +29,mlp.down_proj,0.0001199714,0.05000,7.968 +30,self_attn.k_proj,0.0000238225,0.05000,1.046 +30,self_attn.v_proj,0.0000317723,0.05000,1.045 +30,self_attn.q_proj,0.0001267295,0.05000,1.081 +30,self_attn.o_proj,0.0000166787,0.05000,1.776 +30,mlp.gate_proj,0.0006058461,0.05000,1.123 +30,mlp.up_proj,0.0003959458,0.05000,1.121 +30,mlp.down_proj,0.0001081030,0.05000,8.004 +31,self_attn.k_proj,0.0000196001,0.05000,1.059 +31,self_attn.v_proj,0.0000222575,0.05000,1.054 +31,self_attn.q_proj,0.0001011776,0.05000,1.075 +31,self_attn.o_proj,0.0000166730,0.05000,1.782 +31,mlp.gate_proj,0.0010467220,0.05000,1.145 +31,mlp.up_proj,0.0007263806,0.05000,1.148 +31,mlp.down_proj,0.0001074331,0.05000,8.376 +32,self_attn.k_proj,0.0000057730,0.05000,1.069 +32,self_attn.v_proj,0.0000073269,0.05000,1.055 +32,self_attn.q_proj,0.0000331176,0.05000,1.088 +32,self_attn.o_proj,0.0000133086,0.05000,1.784 +32,mlp.gate_proj,0.0005488825,0.05000,1.131 +32,mlp.up_proj,0.0003933588,0.05000,1.135 +32,mlp.down_proj,0.0001048277,0.05000,8.001 +33,self_attn.k_proj,0.0000048959,0.05000,1.042 +33,self_attn.v_proj,0.0000050340,0.05000,1.052 +33,self_attn.q_proj,0.0000268427,0.05000,1.084 +33,self_attn.o_proj,0.0000099646,0.05000,1.772 +33,mlp.gate_proj,0.0003607540,0.05000,1.121 +33,mlp.up_proj,0.0003298347,0.05000,1.118 +33,mlp.down_proj,0.0001057911,0.05000,7.965 +34,self_attn.k_proj,0.0000065684,0.05000,1.047 +34,self_attn.v_proj,0.0000074894,0.05000,1.048 +34,self_attn.q_proj,0.0000404844,0.05000,1.081 +34,self_attn.o_proj,0.0000151833,0.05000,1.776 +34,mlp.gate_proj,0.0003230668,0.05000,1.140 +34,mlp.up_proj,0.0003079835,0.05000,1.126 +34,mlp.down_proj,0.0000838736,0.05000,8.001 +35,self_attn.k_proj,0.0000077875,0.05000,1.044 +35,self_attn.v_proj,0.0000089657,0.05000,1.038 +35,self_attn.q_proj,0.0000481206,0.05000,1.079 +35,self_attn.o_proj,0.0000184487,0.05000,1.764 +35,mlp.gate_proj,0.0003501297,0.05000,1.120 +35,mlp.up_proj,0.0003335290,0.05000,1.125 +35,mlp.down_proj,0.0000936887,0.05000,8.692 +36,self_attn.k_proj,0.0000049325,0.05000,1.043 +36,self_attn.v_proj,0.0000056771,0.05000,1.044 +36,self_attn.q_proj,0.0000304468,0.05000,1.072 +36,self_attn.o_proj,0.0000143740,0.05000,3.903 +36,mlp.gate_proj,0.0003720354,0.05000,1.124 +36,mlp.up_proj,0.0003543600,0.05000,1.118 +36,mlp.down_proj,0.0001041509,0.05000,8.588 +37,self_attn.k_proj,0.0000100719,0.05000,1.054 +37,self_attn.v_proj,0.0000115485,0.05000,1.049 +37,self_attn.q_proj,0.0000616053,0.05000,1.209 +37,self_attn.o_proj,0.0000252617,0.05000,1.812 +37,mlp.gate_proj,0.0003926754,0.05000,1.200 +37,mlp.up_proj,0.0003614664,0.05000,1.117 +37,mlp.down_proj,0.0001064732,0.05000,7.987 +38,self_attn.k_proj,0.0000067528,0.05000,1.065 +38,self_attn.v_proj,0.0000076714,0.05000,1.060 +38,self_attn.q_proj,0.0000400771,0.05000,1.181 +38,self_attn.o_proj,0.0000220664,0.05000,1.787 +38,mlp.gate_proj,0.0003429898,0.05000,1.140 +38,mlp.up_proj,0.0003293061,0.05000,1.142 +38,mlp.down_proj,0.0001008956,0.05000,8.009 +39,self_attn.k_proj,0.0000061872,0.05000,1.069 +39,self_attn.v_proj,0.0000065399,0.05000,1.068 +39,self_attn.q_proj,0.0000380468,0.05000,1.078 +39,self_attn.o_proj,0.0000231821,0.05000,1.772 +39,mlp.gate_proj,0.0003072655,0.05000,1.135 +39,mlp.up_proj,0.0003144672,0.05000,1.128 +39,mlp.down_proj,0.0000982053,0.05000,8.046 +40,self_attn.k_proj,0.0000075060,0.05000,1.053 +40,self_attn.v_proj,0.0000085450,0.05000,1.047 +40,self_attn.q_proj,0.0000463455,0.05000,1.099 +40,self_attn.o_proj,0.0000311977,0.05000,1.764 +40,mlp.gate_proj,0.0002644811,0.05000,1.130 +40,mlp.up_proj,0.0002856952,0.05000,1.126 +40,mlp.down_proj,0.0000964624,0.05000,7.991 +41,self_attn.k_proj,0.0000073851,0.05000,1.042 +41,self_attn.v_proj,0.0000080522,0.05000,1.045 +41,self_attn.q_proj,0.0000478026,0.05000,1.070 +41,self_attn.o_proj,0.0000302376,0.05000,1.768 +41,mlp.gate_proj,0.0002724422,0.05000,1.130 +41,mlp.up_proj,0.0002986726,0.05000,1.111 +41,mlp.down_proj,0.0000970860,0.05000,7.992 +42,self_attn.k_proj,0.0000100851,0.05000,1.056 +42,self_attn.v_proj,0.0000115108,0.05000,1.053 +42,self_attn.q_proj,0.0000662501,0.05000,1.090 +42,self_attn.o_proj,0.0000333506,0.05000,1.782 +42,mlp.gate_proj,0.0002813541,0.05000,1.348 +42,mlp.up_proj,0.0003163875,0.05000,1.161 +42,mlp.down_proj,0.0001026058,0.05000,8.362 +43,self_attn.k_proj,0.0000145322,0.05000,1.050 +43,self_attn.v_proj,0.0000158925,0.05000,1.048 +43,self_attn.q_proj,0.0000893748,0.05000,1.075 +43,self_attn.o_proj,0.0000389413,0.05000,1.763 +43,mlp.gate_proj,0.0003090515,0.05000,1.137 +43,mlp.up_proj,0.0003404725,0.05000,1.119 +43,mlp.down_proj,0.0002586559,0.05000,7.994 +44,self_attn.k_proj,0.0000218219,0.05000,1.054 +44,self_attn.v_proj,0.0000259004,0.05000,1.055 +44,self_attn.q_proj,0.0001479396,0.05000,1.077 +44,self_attn.o_proj,0.0000474695,0.05000,1.783 +44,mlp.gate_proj,0.0003127389,0.05000,1.128 +44,mlp.up_proj,0.0003464879,0.05000,1.124 +44,mlp.down_proj,0.0001232855,0.05000,8.231 +45,self_attn.k_proj,0.0000227116,0.05000,1.042 +45,self_attn.v_proj,0.0000225401,0.05000,1.042 +45,self_attn.q_proj,0.0001326203,0.05000,1.096 +45,self_attn.o_proj,0.0000609935,0.05000,1.758 +45,mlp.gate_proj,0.0003154614,0.05000,1.142 +45,mlp.up_proj,0.0003421955,0.05000,1.125 +45,mlp.down_proj,0.0001295402,0.05000,8.166 +46,self_attn.k_proj,0.0000203155,0.05000,1.042 +46,self_attn.v_proj,0.0000243960,0.05000,1.040 +46,self_attn.q_proj,0.0001327600,0.05000,1.074 +46,self_attn.o_proj,0.0000586457,0.05000,1.758 +46,mlp.gate_proj,0.0003317181,0.05000,1.153 +46,mlp.up_proj,0.0003596539,0.05000,1.137 +46,mlp.down_proj,0.0001373474,0.05000,7.975 +47,self_attn.k_proj,0.0000287401,0.05000,1.059 +47,self_attn.v_proj,0.0000378734,0.05000,1.049 +47,self_attn.q_proj,0.0001960034,0.05000,1.094 +47,self_attn.o_proj,0.0000479580,0.05000,1.804 +47,mlp.gate_proj,0.0003378080,0.05000,1.130 +47,mlp.up_proj,0.0003639913,0.05000,1.130 +47,mlp.down_proj,0.0001630509,0.05000,8.682 +48,self_attn.k_proj,0.0000326587,0.05000,1.070 +48,self_attn.v_proj,0.0000420830,0.05000,1.069 +48,self_attn.q_proj,0.0002336485,0.05000,1.089 +48,self_attn.o_proj,0.0000797854,0.05000,1.795 +48,mlp.gate_proj,0.0003719960,0.05000,1.677 +48,mlp.up_proj,0.0003905721,0.05000,1.151 +48,mlp.down_proj,0.0001752929,0.05000,8.103 +49,self_attn.k_proj,0.0000346826,0.05000,1.048 +49,self_attn.v_proj,0.0000406586,0.05000,1.054 +49,self_attn.q_proj,0.0002300940,0.05000,1.088 +49,self_attn.o_proj,0.0000726788,0.05000,1.775 +49,mlp.gate_proj,0.0004289962,0.05000,1.136 +49,mlp.up_proj,0.0004409457,0.05000,1.132 +49,mlp.down_proj,0.0002485424,0.05000,7.970 +50,self_attn.k_proj,0.0000364574,0.05000,1.051 +50,self_attn.v_proj,0.0000476124,0.05000,1.045 +50,self_attn.q_proj,0.0002595472,0.05000,1.078 +50,self_attn.o_proj,0.0000738570,0.05000,1.797 +50,mlp.gate_proj,0.0005196592,0.05000,1.125 +50,mlp.up_proj,0.0005209628,0.05000,1.130 +50,mlp.down_proj,0.0004004640,0.05000,8.063 +51,self_attn.k_proj,0.0000649455,0.05000,1.057 +51,self_attn.v_proj,0.0000829220,0.05000,1.049 +51,self_attn.q_proj,0.0004398252,0.05000,1.087 +51,self_attn.o_proj,0.0001423696,0.05000,1.797 +51,mlp.gate_proj,0.0006647636,0.05000,1.153 +51,mlp.up_proj,0.0006608297,0.05000,1.152 +51,mlp.down_proj,0.0006123469,0.05000,8.000 +52,self_attn.k_proj,0.0000878023,0.05000,1.052 +52,self_attn.v_proj,0.0001286716,0.05000,1.054 +52,self_attn.q_proj,0.0006764697,0.05000,1.099 +52,self_attn.o_proj,0.0001523513,0.05000,1.782 +52,mlp.gate_proj,0.0008464120,0.05000,1.124 +52,mlp.up_proj,0.0008526947,0.05000,1.126 +52,mlp.down_proj,0.0008183107,0.05000,8.027 +53,self_attn.k_proj,0.0001403411,0.05000,1.042 +53,self_attn.v_proj,0.0001782136,0.05000,1.037 +53,self_attn.q_proj,0.0009704368,0.05000,1.250 +53,self_attn.o_proj,0.0001480780,0.05000,1.917 +53,mlp.gate_proj,0.0009788685,0.05000,1.131 +53,mlp.up_proj,0.0009995223,0.05000,1.134 +53,mlp.down_proj,0.0012458582,0.05000,8.069 +54,self_attn.k_proj,0.0002222697,0.05000,1.056 +54,self_attn.v_proj,0.0003150965,0.05000,1.046 +54,self_attn.q_proj,0.0015428386,0.05000,1.074 +54,self_attn.o_proj,0.0002995660,0.05000,1.815 +54,mlp.gate_proj,0.0013180814,0.05000,1.135 +54,mlp.up_proj,0.0013410654,0.05000,1.134 +54,mlp.down_proj,0.0016283727,0.05000,7.964 +55,self_attn.k_proj,0.0002455719,0.05000,1.062 +55,self_attn.v_proj,0.0002898146,0.05000,1.053 +55,self_attn.q_proj,0.0016511303,0.05000,1.080 +55,self_attn.o_proj,0.0002813179,0.05000,1.794 +55,mlp.gate_proj,0.0014898408,0.05000,1.446 +55,mlp.up_proj,0.0015437358,0.05000,1.134 +55,mlp.down_proj,0.0021947372,0.05000,8.029 +56,self_attn.k_proj,0.0004278187,0.05000,1.041 +56,self_attn.v_proj,0.0006316985,0.05000,1.039 +56,self_attn.q_proj,0.0029827804,0.05000,1.061 +56,self_attn.o_proj,0.0003085413,0.05000,1.788 +56,mlp.gate_proj,0.0017243970,0.05000,1.164 +56,mlp.up_proj,0.0018149042,0.05000,1.149 +56,mlp.down_proj,0.0027739530,0.05000,8.076 +57,self_attn.k_proj,0.0005359473,0.05000,1.052 +57,self_attn.v_proj,0.0008049904,0.05000,1.044 +57,self_attn.q_proj,0.0038959943,0.05000,1.090 +57,self_attn.o_proj,0.0003918819,0.05000,1.765 +57,mlp.gate_proj,0.0018884934,0.05000,1.139 +57,mlp.up_proj,0.0020396879,0.05000,1.125 +57,mlp.down_proj,0.0037069661,0.05000,7.999 +58,self_attn.k_proj,0.0008708814,0.05000,1.038 +58,self_attn.v_proj,0.0013238839,0.05000,1.060 +58,self_attn.q_proj,0.0062347704,0.05000,1.074 +58,self_attn.o_proj,0.0004224728,0.05000,1.770 +58,mlp.gate_proj,0.0021498542,0.05000,1.140 +58,mlp.up_proj,0.0023638556,0.05000,1.122 +58,mlp.down_proj,0.0048660359,0.05000,8.354 +59,self_attn.k_proj,0.0010695715,0.05000,1.045 +59,self_attn.v_proj,0.0017025579,0.05000,1.064 +59,self_attn.q_proj,0.0078237816,0.05000,1.083 +59,self_attn.o_proj,0.0004261862,0.05000,1.775 +59,mlp.gate_proj,0.0023862109,0.05000,1.255 +59,mlp.up_proj,0.0026503182,0.05000,1.144 +59,mlp.down_proj,0.0074393693,0.05000,8.122 +60,self_attn.k_proj,0.0011864857,0.05000,1.072 +60,self_attn.v_proj,0.0017836547,0.05000,1.071 +60,self_attn.q_proj,0.0079164522,0.05000,1.096 +60,self_attn.o_proj,0.0012012388,0.05000,1.808 +60,mlp.gate_proj,0.0025860246,0.05000,1.145 +60,mlp.up_proj,0.0029487530,0.05000,1.143 +60,mlp.down_proj,0.0112182335,0.05000,8.058 +61,self_attn.k_proj,0.0015718682,0.05000,1.049 +61,self_attn.v_proj,0.0026914134,0.05000,1.048 +61,self_attn.q_proj,0.0114342334,0.05000,1.076 +61,self_attn.o_proj,0.0012516713,0.05000,1.786 +61,mlp.gate_proj,0.0027420398,0.05000,1.126 +61,mlp.up_proj,0.0031601495,0.05000,1.142 +61,mlp.down_proj,0.0159969039,0.05000,7.986 +62,self_attn.k_proj,0.0016475655,0.05000,1.066 +62,self_attn.v_proj,0.0028598230,0.05000,1.049 +62,self_attn.q_proj,0.0114434291,0.05000,1.073 +62,self_attn.o_proj,0.0022906732,0.05000,1.797 +62,mlp.gate_proj,0.0033809583,0.05000,1.133 +62,mlp.up_proj,0.0037481985,0.05000,1.126 +62,mlp.down_proj,0.0255297494,0.05000,8.035 +63,self_attn.k_proj,0.0007640351,0.05000,1.059 +63,self_attn.v_proj,0.0011615969,0.05000,1.046 +63,self_attn.q_proj,0.0052693927,0.05000,1.076 +63,self_attn.o_proj,0.0020771761,0.05000,1.768 +63,mlp.gate_proj,0.0041764780,0.05000,1.125 +63,mlp.up_proj,0.0045288563,0.05000,1.131 +63,mlp.down_proj,0.0907532932,0.05000,8.077 diff --git a/quantize_config.json b/quantize_config.json new file mode 100644 index 0000000..d5fce9f --- /dev/null +++ b/quantize_config.json @@ -0,0 +1,24 @@ +{ + "bits": 4, + "group_size": 128, + "desc_act": false, + "sym": true, + "lm_head": false, + "quant_method": "gptq", + "checkpoint_format": "gptq", + "pack_dtype": "int32", + "meta": { + "quantizer": [ + "gptqmodel:4.2.5" + ], + "uri": "https://github.com/modelcloud/gptqmodel", + "damp_percent": 0.05, + "damp_auto_increment": 0.01, + "static_groups": false, + "true_sequential": true, + "mse": 0.0, + "v2": false, + "v2_alpha": 0.25, + "act_group_aware": false + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..82d7bbe --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,25 @@ +{ + "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": "<|endoftext|>" +} 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..b1037b3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,241 @@ +{ + "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|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2TokenizerFast", + "unk_token": null, + "_commit_hash": null +} \ No newline at end of file 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