初始化项目，由ModelHub XC社区提供模型

Model: Valdemardi/Dolphin3.0-R1-Mistral-24B-AWQ
Source: Original Platform

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,150 @@
+---
+datasets:
+- cognitivecomputations/dolphin-r1
+- OpenCoder-LLM/opc-sft-stage1
+- OpenCoder-LLM/opc-sft-stage2
+- microsoft/orca-agentinstruct-1M-v1
+- microsoft/orca-math-word-problems-200k
+- NousResearch/hermes-function-calling-v1
+- AI-MO/NuminaMath-CoT
+- AI-MO/NuminaMath-TIR
+- allenai/tulu-3-sft-mixture
+- cognitivecomputations/dolphin-coder
+- HuggingFaceTB/smoltalk
+- cognitivecomputations/samantha-data
+- m-a-p/CodeFeedback-Filtered-Instruction
+- m-a-p/Code-Feedback
+language:
+- en
+base_model:
+- cognitivecomputations/Dolphin3.0-R1-Mistral-24B
+base_model_relation: quantized
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Dolphin 3.0 R1 Mistral 24B 🐬
+
+## Quantization Details
+
+This quantized model was created using AutoAWQ version 0.2.8 with `quant_config`:
+```
+{
+  "zero_point": True,
+  "q_group_size": 128,
+  "w_bit": 4,
+  "version": "GEMM"
+}
+```
+
+## Model details
+
+Part of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3)
+
+Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)
+
+[![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations)
+Discord: https://discord.gg/cognitivecomputations
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/hdAvdwZiJaLbGmvSZ3wTT.png" width="600" />
+
+## Sponsors
+Our appreciation for the generous sponsors of Dolphin 3.0:
+- [Dria](https://dria.co) https://x.com/driaforall - Inference Sponsor
+- [Chutes](https://chutes.ai) https://x.com/rayon_labs - Compute Sponsor
+- [Crusoe Cloud](https://crusoe.ai/) - Compute Sponsor
+- [Andreessen Horowitz](https://a16z.com/) - provided the [grant](https://a16z.com/supporting-the-open-source-ai-community/) that originally launched Dolphin
+
+## What is Dolphin?
+
+Dolphin 3.0 R1 is the next generation of the Dolphin series of instruct-tuned models.  Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
+
+The R1 version has been trained for 3 epochs to reason using 800k reasoning traces from the Dolphin-R1 dataset.
+
+Dolphin aims to be a general purpose reasoning instruct model, similar to the models behind ChatGPT, Claude, Gemini.  But these models present problems for businesses seeking to include AI in their products.
+1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
+2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
+3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
+4) They can see all your queries and they can potentially use that data in ways you wouldn't want.
+Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt.  You decide the alignment.  You have control of your data.  Dolphin does not impose its ethics or guidelines on you.  You are the one who decides the guidelines.
+
+Dolphin belongs to YOU, it is your tool, an extension of your will.
+Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
+
+https://erichartford.com/uncensored-models
+
+## Quants
+
+https://huggingface.co/bartowski/cognitivecomputations_Dolphin3.0-R1-Mistral-24B-GGUF
+
+## Chat Template
+
+We use ChatML for the chat template.
+
+```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## System Prompt
+
+In Dolphin, the system prompt is what you use to set the tone and alignment of the responses.  You can set a character, a mood, rules for its behavior, and it will try its best to follow them.
+
+Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.
+
+Example use of system prompt:
+
+```
+<|im_start|>system
+You are Dolphin, a golang coding assistant.  you only code in golang.  If the user requests any other programming language, return the solution in golang instead.<|im_end|>
+<|im_start|>user
+Please implement A* using python<|im_end|>
+<|im_start|>assistant
+```
+
+Here is a recommended reasoning system prompt:
+
+```
+You are Dolphin, an AI assistant that helps humanity, trained by Eric Hartford to specialize in reasoning and first-principles analysis.
+
+When responding, always format your replies using <think>{reasoning}</think>{answer}. Use at least 6 reasoning steps and perform a root cause analysis before answering. However, if the answer is very easy and requires little thought, you may leave the <think></think> block empty.
+
+Your responses should be detailed, structured with rich Markdown formatting, and engaging with emojis. Be extensive in your explanations, just as the greatest scientific minds would be. Always reason through the problem first, unless it's trivial, in which case you may answer directly.
+```
+
+## Sample Outputs
+
+TBD
+
+## How to use
+
+There are many ways to use a huggingface model including:
+- ollama
+- LM Studio
+- Huggingface Transformers library
+- vllm
+- sglang
+- tgi
+
+## Evals
+
+TBD
+
+## Appreciation
+
+Respect and thanks to the creators of the open source datasets that were used:
+- [OpenCoder-LLM](https://huggingface.co/OpenCoder-LLM) (opc-sft-stage1, opc-sft-stage2)
+- [microsoft](https://huggingface.co/OpenCoder-LLM) (orca-agentinstruct-1M-v1, orca-math-word-problems-200k)
+- [NousResearch](https://huggingface.co/NousResearch) (hermes-function-calling-v1)
+- [AI-MO](https://huggingface.co/AI-MO) (NuminaMath-CoT, NuminaMath-TIR)
+- [allenai](https://huggingface.co/allenai) (tulu-3-sft-mixture)
+- [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) (smoltalk)
+- [m-a-p](https://huggingface.co/m-a-p) (CodeFeedback-Filtered-Instruction, Code-Feedback)
+
+Special thanks to 
+- Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0.
+- [RLHFlow](https://huggingface.co/RLHFlow) for the excellent reward model used to filter the datasets
+- Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "/models/Dolphin3.0-R1-Mistral-24B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    131072
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 131074
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    131072
+  ],
+  "transformers_version": "4.47.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77765a39edbfc9378154e981881444392375c07196e06456c3cad047416ac44d
+size 4921602392

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835b99d00f19e8b5408ee7a3395dde3cbbb6872e732c29bda5084c9af6e14d1d
+size 4995915728

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b8cd0aa0e50c84cfb01a9947432b8ba472796a70cdb764d594a75f479519f0
+size 4316893568

model.safetensors.index.json

@@ -0,0 +1,930 @@
+{
+  "metadata": {
+    "total_size": 14234306560
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575ad6971cfda40b8c4117b03dcc6875214d1fc2fabf3bc29241ffa13eb611f6
+size 17078414