commit 302c0c916f437eb2a6c4b50555f855a5398f4c7b
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Oct 8 21:40:15 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: tclf90/Codestral-22B-v0.1-hf-GPTQ-Int4
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..7bc225d
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,34 @@
+*.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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/LICENSE b/LICENSE
new file mode 100755
index 0000000..ca8b7fc
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,79 @@
+# Mistral AI Non-Production License
+
+## 1. Scope and acceptance
+
+**1.1. Scope of the Agreement.**
+This Agreement applies to any use, modification, or Distribution of any Mistral Model by You, regardless of the source You obtained a copy of such Mistral Model.
+
+**1.2. Acceptance.** By accessing, using, modifying, Distributing a Mistral Model, or by creating, using or distributing a Derivative of the Mistral Model, You agree to be bound by this Agreement.
+
+**1.3. Acceptance on behalf of a third-party.** If You accept this Agreement on behalf of Your employer or another person or entity, You warrant and represent that You have the authority to act and accept this Agreement on their behalf. In such a case, the word “You” in this Agreement will refer to Your employer or such other person or entity.
+
+## 2. License
+**2.1. Grant of rights.** Subject to Section 3 below, Mistral AI hereby grants You a non-exclusive, royalty-free, worldwide, non-sublicensable, non-transferable, limited license to use, copy, modify, and Distribute under the conditions provided in Section 2.2 below, the Mistral Model and any Derivatives made by or for Mistral AI and to create Derivatives of the Mistral Model.
+
+**2.2. Distribution of Mistral Model and Derivatives made by or for Mistral AI.** Subject to Section 3 below, You may Distribute copies of the Mistral Model and/or Derivatives made by or for Mistral AI, under the following conditions:
+- You must make available a copy of this Agreement to third-party recipients of the Mistral Models and/or Derivatives made by or for Mistral AI you Distribute, it being specified that any rights to use the Mistral Models and/or Derivatives made by or for Mistral AI shall be directly granted by Mistral AI to said third-party recipients pursuant to the Mistral AI Non-Production License agreement executed between these parties;
+- You must retain in all copies of the Mistral Models the following attribution notice within a “Notice” text file distributed as part of such copies: “Licensed by Mistral AI under the Mistral AI Non-Production License”.
+
+**2.3. Distribution of Derivatives made by or for You.** Subject to Section 3 below, You may Distribute any Derivatives made by or for You under additional or different terms and conditions, provided that:
+- In any event, the use and modification of Mistral Model and/or Derivatives made by or for Mistral AI shall remain governed by the terms and conditions of this Agreement;
+- You include in any such Derivatives made by or for You prominent notices stating that You modified the concerned Mistral Model; and
+- Any terms and conditions You impose on any third-party recipients relating to Derivatives made by or for You shall neither limit such third-party recipients’ use of the Mistral Model or any Derivatives made by or for Mistral AI in accordance with the Mistral AI Non-Production License nor conflict with any of its terms and conditions.
+
+## 3. Limitations
+**3.1. Misrepresentation.** You must not misrepresent or imply, through any means, that the Derivatives made by or for You and/or any modified version of the Mistral Model You Distribute under your name and responsibility is an official product of Mistral AI or has been endorsed, approved or validated by Mistral AI, unless You are authorized by Us to do so in writing.
+
+**3.2. Usage Limitation**
+- You shall only use the Mistral Models and Derivatives (whether or not created by Mistral AI) for testing, research, Personal, or evaluation purposes in Non-Production Environments;
+- Subject to the foregoing, You shall not supply the Mistral Models or Derivatives in the course of a commercial activity, whether in return for payment or free of charge, in any medium or form, including but not limited to through a hosted or managed service (e.g. SaaS, cloud instances, etc.), or behind a software layer.
+
+**3.3. Usage not permitted under this Agreement.** If You want to use a Mistral Model or a Derivative for any purpose that is not expressly authorized under this Agreement, You must request a license from Mistral AI, which Mistral AI may grant to You in Mistral AI’s sole discretion. Please contact Mistral AI at the following e-mail address if You want to discuss such a license: license@mistral.ai
+
+## 4. Intellectual Property
+**4.1. Trademarks.** No trademark licenses are granted under this Agreement, and in connection with the Mistral Models, You may not use any name or mark owned by or associated with Mistral AI or any of its affiliates, except (i) as required for reasonable and customary use in describing and Distributing the Mistral Models and Derivatives made by or for Mistral AI and (ii) for attribution purposes as required by this Agreement.
+
+**4.2. Outputs.** We claim no ownership rights in and to the Outputs. You are solely responsible for the Outputs You generate and their subsequent uses in accordance with this Agreement.
+
+**4.3. Derivatives.** By entering into this Agreement, You accept that any Derivatives that You may create or that may be created for You shall be subject to the restrictions set out in Section 3 of this Agreement.
+
+# 5. Liability
+**5.1. Limitation of liability.** In no event, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall Mistral AI be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this Agreement or out of the use or inability to use the Mistral Models and Derivatives (including but not limited to damages for loss of data, loss of goodwill, loss of expected profit or savings, work stoppage, computer failure or malfunction, or any damage caused by malware or security breaches), even if  Mistral AI has been advised of the possibility of such damages.
+
+**5.2. Indemnification.** You agree to indemnify and hold harmless Mistral AI from and against any claims, damages, or losses arising out of or related to Your use or Distribution of the Mistral Models and Derivatives.
+
+## 6. Warranty
+**6.1. Disclaimer.** Unless required by applicable law or agreed to in writing, Mistral AI provides the Mistral Models and Derivatives on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. Mistral AI does not represent nor warrant that the Mistral Models and Derivatives will be error-free, meet Your or any third party’s requirements, be secure or will allow You or any third party to achieve any kind of result or generate any kind of content. You are solely responsible for determining the appropriateness of using or Distributing the Mistral Models and Derivatives and assume any risks associated with Your exercise of rights under this Agreement.
+
+# 7. Termination
+**7.1. Term.** This Agreement is effective as of the date of your acceptance of this Agreement or access to the concerned Mistral Models or Derivatives and will continue until terminated in accordance with the following terms.
+
+**7.2. Termination.** Mistral AI may terminate this Agreement at any time if You are in breach of this Agreement. Upon termination of this Agreement, You must cease to use all Mistral Models and Derivatives and shall permanently delete any copy thereof. Sections 5, 6, 7 and 8 shall survive the termination of this Agreement.
+
+**7.3. Litigation.** If You initiate any legal action or proceedings against Us or any other entity (including a cross-claim or counterclaim in a lawsuit), alleging that the Model or a Derivative, or any part thereof, infringe upon intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement will immediately terminate as of the date such legal action or claim is filed or initiated.
+
+# 8. General provisions
+**8.1. Governing laws.** This Agreement will be governed by the laws of France, without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+
+**8.2. Competent jurisdiction.** The courts of Paris shall have exclusive jurisdiction of any dispute arising out of this Agreement.
+
+**8.3. Severability.** If any provision of this Agreement is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
+
+# 9. Definitions
+**“Agreement”**: means this Mistral AI Non-Production License agreement governing the access, use, and Distribution of the Mistral Models and Derivatives.
+
+**“Derivative”**: means any (i) modified version of the Mistral Model (including but not limited to any customized or fine-tuned version thereof), (ii) work based on the Mistral Model, or (iii) any other derivative work thereof. For the avoidance of doubt, Outputs are not considered as Derivatives under this Agreement.
+
+**“Distribution”**, **“Distributing”**, **“Distribute”** or **“Distributed”**: means providing or making available, by any means, a copy of the Mistral Models and/or the Derivatives as the case may be, subject to Section 3 of this Agreement.
+
+**“Mistral AI”**, **“We”** or **“Us”**: means Mistral AI, a French société par actions simplifiée registered in the Paris commercial registry under the number 952 418 325, and having its registered seat at 15, rue des Halles, 75001 Paris.
+
+**“Mistral Model”**: means the foundational large language model(s), and its elements which include algorithms, software, instructed checkpoints, parameters, source code (inference code, evaluation code and, if applicable, fine-tuning code) and any other elements associated thereto made available by Mistral AI under this Agreement, including, if any, the technical documentation, manuals and instructions for the use and operation thereof.
+
+**“Non-Production Environment”**: means any setting, use case, or application of the Mistral Models or Derivatives that expressly excludes live, real-world conditions, commercial operations, revenue-generating activities, or direct interactions with or impacts on end users (such as, for instance, Your employees or customers). Non-Production Environment may include, but is not limited to, any setting, use case, or application for research, development, testing, quality assurance, training, internal evaluation (other than any internal usage by employees in the context of the company’s business activities), and demonstration purposes.
+
+**“Outputs”**: means any content generated by the operation of the Mistral Models or the Derivatives from  a prompt (i.e., text instructions) provided by users. For the avoidance of doubt, Outputs do not include any components of a Mistral Models, such as any fine-tuned versions of the Mistral Models, the weights, or parameters.
+
+**“Personal”**: means any use of a Mistral Model or a Derivative that is (i) solely for personal, non-profit and non-commercial purposes and (ii) not directly or indirectly connected to any commercial activities, business operations, or employment responsibilities. For illustration purposes, Personal use of a Model or a Derivative does not include any usage by individuals employed in companies in the context of their daily tasks, any activity that is intended to generate revenue, or that is performed on behalf of a commercial entity.
+
+**“You”**: means the individual or entity entering into this Agreement with Mistral AI.
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..f92ac98
--- /dev/null
+++ b/README.md
@@ -0,0 +1,116 @@
+---
+license: MNPL-0.1
+license_name: Mistral AI Non-Production License
+license_link: LICENSE
+pipeline_tag: text-generation
+tags:
+- codestral
+- gptq
+- int4
+- 量化修复
+- vLLM
+---
+
+# Codestral-22B-v0.1-hf-GPTQ-Int4-量化修复
+Hugging Face 原模型 [mistralai/Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1)
+
+
+### 【模型更新日期】
+``` 2024-05-30 ```
+
+### 【模型大小】
+`12.2GB`
+
+### 【介绍】
+Mistral发布的首个代码生成模型Codestral，精通80+编程语言。注意非商用授权。
+
+### 【量化修复】
+
+调优了现有 `AWQ` 与 `GPTQ` 量化算法的量化策略。带有`量化修复`标签的`Int3`模型，可以比肩默认`AWQ`与`GPTQ`算法的`Int8`模型的能力。
+
+1. 量化修复可以极大减少模型的`1.乱吐字`、`2.无限循环`、`3.长文能力丢失`等量化损失造成的模型不可用的情况。
+
+2. 调优后的量化模型，`AWQ`与`GPTQ`模型在能力上没有表现出明显区别。同时考虑到`GPTQ`的`vLLM`引擎的并发推理效率最好，所以不再制作`AWQ`模型。
+
+
+
+### 【同期量化修复模型】
+
+| 模型名称                                                                                                                            | 磁盘大小（GB） |
+|---------------------------------------------------------------------------------------------------------------------------------|----------|
+| [零一万物-1.5-6B-Chat-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Yi-1.5-6B-Chat-GPTQ-Int3)                             | 3.3      |
+| [零一万物-1.5-9B-Chat-16K-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Yi-1.5-9B-Chat-16K-GPTQ-Int3)                     | 4.4      |
+| [零一万物-1.5-34B-Chat-16K-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Yi-1.5-34B-Chat-16K-GPTQ-Int3)                   | 15.1     |
+| [通义千问1.5-7B-Chat-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Qwen1.5-7B-Chat-GPTQ-Int3)                             | 5.1      |
+| [通义千问1.5-14B-Chat-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Qwen1.5-14B-Chat-GPTQ-Int3)                           | 8.1      |
+| [通义千问1.5-32B-Chat-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Qwen1.5-32B-Chat-GPTQ-Int3)                           | 15.4     |
+| [通义千问1.5-72B-Chat-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Qwen1.5-72B-Chat-GPTQ-Int3)                           | 32.5     |
+| [通义千问1.5-110B-Chat-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/Qwen1.5-110B-Chat-GPTQ-Int3)                         | 47.9     |
+| [openbuddy-llama3-70b-v21.1-8k-GPTQ-Int3-量化修复](https://www.modelscope.cn/models/tclf90/openbuddy-llama3-70b-v21.1-8k-GPTQ-Int3) | 31.5     |
+
+
+### 【模型下载】
+```python
+from modelscope import snapshot_download
+model_dir = snapshot_download('tclf90/模型名', cache_dir="本地路径")
+```
+
+### 【[vLLM](https://github.com/vllm-project/vllm)推理（目前仅限Linux）】
+#### 1. Python 简易调试
+
+```python
+from transformers import AutoTokenizer
+from vllm import LLM, SamplingParams
+
+max_model_len, tp_size = 4000, 1
+model_name = "本地路径/tclf90/模型名称"   # 例："./my_models/tclf90/Qwen1.5-32B-Chat-GPTQ-Int3"
+model_name = model_name.replace('.', '___')
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True, enforce_eager=True)
+sampling_params = SamplingParams(temperature=0.7, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
+
+messages_list = [
+    [{"role": "user", "content": "你是谁"}],
+    [{"role": "user", "content": "介绍一下你自己"}],
+    [{"role": "user", "content": "用python写一个快排函数"}],
+]
+
+prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
+
+outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
+
+generated_text = [output.outputs[0].text for output in outputs]
+print(generated_text)
+```
+
+#### 2. 类ChatGPT RESTFul API Server
+```
+>>> python -m vllm.entrypoints.openai.api_server --model 本地路径/tclf90/模型名称
+```
+
+### 【Transformer推理】
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+model_name = "本地路径/tclf90/模型名称"   # 例："./my_models/tclf90/Qwen1.5-32B-Chat-GPTQ-Int3"
+model_name = model_name.replace('.', '___')
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
+model.generation_config = GenerationConfig.from_pretrained(model_name)
+model.generation_config.pad_token_id = model.generation_config.eos_token_id
+
+messages = [
+    {"role": "user", "content": "你好你是谁"}
+]
+input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
+
+result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
+print(result)
+```
+
+
+
+
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..4560c41
--- /dev/null
+++ b/config.json
@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "tclf90/Codestral-22B-v0.1-hf-GPTQ-Int4",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true,
+    "use_exllama": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
\ No newline at end of file
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..827fe2d
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1,4 @@
+{
+  "framework": "Pytorch",
+  "task": "text-generation"
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..7048d41
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.1"
+}
diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors
new file mode 100644
index 0000000..bfcc289
--- /dev/null
+++ b/model-00001-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9878dba320fac7f77c92c528ed9413ec3fbdc6c41a7cf31e5e0392079bf6734
+size 4966960768
diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors
new file mode 100644
index 0000000..291672d
--- /dev/null
+++ b/model-00002-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861533c757b1feaafd19852a9372a57d507f076c874f3fd974792fcaca004764
+size 4999726768
diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors
new file mode 100644
index 0000000..8a5200a
--- /dev/null
+++ b/model-00003-of-00003.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2496ed945274b633c79a19d8d16a1f918699c4a7b86d26c05ed37049f393961
+size 2206737848
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..16027bd
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,2082 @@
+{
+  "metadata": {
+    "total_size": 12173193216
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.g_idx": "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.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.g_idx": "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.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.g_idx": "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.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.g_idx": "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.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.g_idx": "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.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.g_idx": "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.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.g_idx": "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.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.g_idx": "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.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.g_idx": "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.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.g_idx": "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.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.g_idx": "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.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.g_idx": "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.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.g_idx": "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.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.g_idx": "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.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.g_idx": "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.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.g_idx": "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.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.g_idx": "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.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.53.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.54.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.down_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.gate_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.up_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.o_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
+    "model.layers.55.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.g_idx": "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.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.g_idx": "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.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.g_idx": "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.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.g_idx": "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.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.g_idx": "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.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.g_idx": "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.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.g_idx": "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.o_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.g_idx": "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.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.g_idx": "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.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.g_idx": "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.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..451134b
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..f3b30c0
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..8055981
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}