初始化项目，由ModelHub XC社区提供模型

Model: Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound-awq-inc
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,292 @@
+---
+license: mit
+datasets:
+- NeelNanda/pile-10k
+base_model:
+- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+
+---
+
+
+## Model Details
+
+This model is an int4 model with group_size 128 and symmetric quantization of [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. 
+
+Please follow the license of the original model.
+
+## How To Use
+
+**INT4 Inference on CPU/Intel GPU/CUDA**
+
+~~~python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+quantized_model_dir = "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound-awq-inc"
+
+model = AutoModelForCausalLM.from_pretrained(
+    quantized_model_dir,
+    torch_dtype="auto",
+    device_map="auto",
+)
+
+tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, trust_remote_code=True)
+prompts = [
+    "9.11和9.8哪个数字大",
+    "How many e in word deepseek",
+    "There are ten birds in a tree. A hunter shoots one. How many are left in the tree?",
+]
+
+texts = []
+for prompt in prompts:
+    messages = [
+        {"role": "user", "content": prompt}  ##change this to align with the official usage
+    ]
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+    texts.append(text)
+inputs = tokenizer(texts, return_tensors="pt", padding=True, truncation=True)
+
+outputs = model.generate(
+    input_ids=inputs["input_ids"].to(model.device),
+    attention_mask=inputs["attention_mask"].to(model.device),
+    max_length=512,  ##change this to align with the official usage
+    num_return_sequences=1,
+    do_sample=False  ##change this to align with the official usage
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs["input_ids"], outputs)
+]
+
+decoded_outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
+
+for i, prompt in enumerate(prompts):
+    input_id = inputs
+    print(f"Prompt: {prompt}")
+    print(f"Generated: {decoded_outputs[i]}")
+    print("-" * 50)
+
+"""
+Prompt: 9.11和9.8哪个数字大
+Generated: <think>
+首先，用户的问题是：“9.11和9.8哪个数字大？”这是一个比较两个数字大小的问题。
+
+数字是9.11和9.8。9.11是九点一一，9.8是九点八。
+
+在比较小数时，我们需要考虑小数点后的位数。9.11有两位小数，9.8有一位小数，但我们可以将它们视为相同的小数位数来比较。
+
+9.8可以写成9.80，这样就有两位小数了。所以，9.80和9.11。
+
+现在，比较9.80和9.11。整数部分相同，都是9。所以，我们需要比较小数部分。
+
+小数部分：9.80的十分位是8，百分位是0；9.11的十分位是1，百分位是1。
+
+从十分位开始比较：8 vs 1，8大于1，所以9.80大于9.11。
+
+因此，9.8大于9.11。
+
+用户可能是在考虑日期或版本号，但问题明确是“数字”，所以应该作为数值来比较。
+
+在数值上，9.8是9.80，而9.11是9.11，所以9.80 > 9.11。
+
+确认一下：9.8 = 9 + 8/10 = 9.80，而9.11 = 9 + 1/10 + 1/100 = 9.11。
+
+是的，9.80比9.11大。
+
+如果用户是在考虑字符串比较，比如版本号，那么9.11可能被视为9.11，而9.8被视为9.8，但在版本号比较中，通常是从左到右比较数字部分。
+
+例如，在软件版本中，9.8可能被视为9.8.0，所以比较9.11和9.8.0。
+
+9.11的主版本是9，次版本是11；9.8的主版本是9，次版本是8。
+
+所以，主版本相同，次版本11大于8，因此9.11大于9.8。
+
+但问题中说的是“数字
+--------------------------------------------------
+Prompt: How many e in word deepseek
+Generated: <think>
+First, the user asked: "How many e in word deepseek". I need to count the number of 'e's in the word "deepseek".
+
+Let me write down the word: D-E-E-P-S-E-E-K.
+
+Now, I'll go through each letter and count the 'e's.
+
+- D: not e
+
+- E: e (first one)
+
+- E: e (second one)
+
+- P: not e
+
+- S: not e
+
+- E: e (third one)
+
+- E: e (fourth one)
+
+- K: not e
+
+So, there are four 'e's in "deepseek".
+
+I should confirm the spelling. "Deepseek" – is that the correct spelling? I think it's a company name or something, but based on the query, it's given as "deepseek", so I'll assume that's the word.
+
+Also, the user said "e in word", which might be a typo or shorthand for "e's in the word". Probably, they meant "how many e's are in the word deepseek".
+
+Now, to respond, I should be clear and direct. Since this is a simple count, I can just state the number.
+
+But let me make sure there's no trick here. Is "deepseek" meant to be "DeepSeek" or something else? The query says "deepseek", so I'll treat it as a lowercase word for counting purposes.
+
+Perhaps it's a reference to the AI model DeepSeek, but I think for this question, it's just about the word itself.
+
+So, counting: positions with 'e' are 2nd, 3rd, 6th, and 7th letters. That's four.
+
+I can also think of it as the word has 8 letters, and 'e' appears at indices 2,3,6,7 if we start counting from 1.
+
+But for the response, I don't need to be too technical.
+
+Finally, I should phrase my response to be helpful and engaging, but since the question is straightforward, a simple answer might suffice.
+
+Response: There are 4 'e's in the word "deepseek".
+</think>
+The word "deepseek" contains **4** instances of the letter "e". 
+
+To break it down:
+- The word is spelled: D-E-E-P-S-E
+--------------------------------------------------
+Prompt: There are ten birds in a tree. A hunter shoots one. How many are left in the tree?
+Generated: <think>
+First, the question is: "There are ten birds in a tree. A hunter shoots one. How many are left in the tree?"
+
+This seems like a riddle. The straightforward answer might be nine, but I think there's a trick here. Riddles often play on words or assumptions.
+
+Let me read it carefully. "There are ten birds in a tree." Then, "A hunter shoots one." And it asks how many are left.
+
+Now, when a hunter shoots a bird, does that mean the bird dies and falls out of the tree? Or does it fly away? That's a common point in these kinds of riddles.
+
+The classic version of this riddle is: "There are 10 birds in a tree. A hunter shoots one. How many are left?" And the answer is zero because the sound of the gunshot scares the others away.
+
+But in this case, it's similar. Let me confirm the wording. "A hunter shoots one." It doesn't specify if the shot is heard or if the birds are scared.
+
+However, in the standard riddle, the implication is that the shot scares the remaining birds, so they fly away, leaving none.
+
+But here, it just says "shoots one," not necessarily that the shot is loud or that the birds are scared. Maybe I should consider the context.
+
+Perhaps it's about the birds being alive or dead. But the question is about how many are left in the tree, not how many are alive.
+
+Another angle: maybe the hunter is shooting at the birds, but not necessarily hitting them or causing them to leave. But that seems less likely.
+
+Let's think step by step.
+
+Initially, there are ten birds in the tree.
+
+Hunter shoots one. What happens to that one? It's shot, so probably it dies or falls down.
+
+But the question is about how many are left, meaning remaining in the tree.
+
+If the shot kills the bird, it might fall from the tree, so it's no longer in the tree.
+
+Then, the other nine might be scared and fly away.
+
+But the riddle doesn't say that the shot scares the birds; it just says the hunter shoots one.
+
+In many versions, the key is that the shot scares the birds, so they all fly away.
+
+But let's see if there's another interpretation.
+
+Perhaps the birds are not real birds; maybe it's a
+--------------------------------------------------
+"""
+
+~~~
+
+### vLLM usage
+
+~~~python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Hello, my name is",
+]
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)  ##change this to match official usage
+model_name = "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound-awq-inc"
+llm = LLM(model=model_name, tensor_parallel_size=1)
+
+outputs = llm.generate(prompts, sampling_params)
+
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+~~~
+
+
+### Evaluate the model
+
+~~~bash
+auto-round --eval  --model "Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound-inc" --eval_bs 16  --tasks leaderboard_ifeval,leaderboard_mmlu_pro,gsm8k,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,cmmlu,ceval-valid
+~~~
+
+
+
+| Metric               | BF16   | INT4(auto-round) | INT4 (auto-round-best) |
+| -------------------- | ------ | ---------------- | ---------------------- |
+| Avg                  | 0.5958 | 0.5913           | 0.5926                 |
+| arc_challenge        | 0.5137 | 0.5102           | 0.5043                 |
+| arc_easy             | 0.7908 | 0.7862           | 0.7921                 |
+| boolq                | 0.8498 | 0.8526           | 0.8443                 |
+| ceval-valid          | 0.7296 | 0.7177           | 0.7140                 |
+| cmmlu                | 0.7159 | 0.7029           | 0.7027                 |
+| gsm8k                | 0.8211 | 0.8029           | 0.8234                 |
+| hellaswag            | 0.5781 | 0.5703           | 0.5670                 |
+| lambada_openai       | 0.5544 | 0.5490           | 0.5626                 |
+| leaderboard_ifeval   | 0.2731 | 0.2729           | 0.2542                 |
+| leaderboard_mmlu_pro | 0.4115 | 0.4105           | 0.4117                 |
+| openbookqa           | 0.3020 | 0.3060           | 0.3100                 |
+| piqa                 | 0.7617 | 0.7617           | 0.7612                 |
+| truthfulqa_mc1       | 0.3562 | 0.3611           | 0.3696                 |
+| winogrande           | 0.6835 | 0.6740           | 0.6788                 |
+
+
+
+### Reproduce the model
+
+Here is the sample command to reproduce the model
+
+```bash
+auto-round
+--model_name deepseek-ai/DeepSeek-R1-0528-Qwen3-8B \
+--device 0 \
+--format "auto_gptq,auto_awq,auto_round" \
+--enable_torch_compile \
+--output_dir "./tmp_autoround" 
+```
+
+
+
+## Ethical Considerations and Limitations
+
+The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
+
+Therefore, before deploying any applications of the model, developers should perform safety testing.
+
+## Caveats and Recommendations
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
+
+Here are a couple of useful links to learn more about Intel's AI software:
+
+- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
+
+## Disclaimer
+
+The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
+
+## Cite
+
+@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
+
+[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)

chat_template.jinja

@@ -0,0 +1,14 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
+
+' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
+' + '```json' + '
+' + tool['function']['arguments'] + '
+' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
+' + '```json' + '
+' + tool['function']['arguments'] + '
+' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
+' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
+' + '```json' + '
+' + tool['function']['arguments'] + '
+' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
+<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "autoround_version": "0.5.1",
+    "bits": 4,
+    "data_type": "int",
+    "group_size": 128,
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "quant_method": "awq",
+    "sym": true,
+    "version": "gemm",
+    "zero_point": false
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "attn_factor": 0.8782488562869419,
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn"
+  },
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.52.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af72c4000b602bf970633e0c079511db3931a91f21aec01bf2d6cbf65a831f12
+size 4853921768

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdb0a536e6049f478b10a4f5499e59882feecdba779352c353c25a344f166ac
+size 1244659840

model.safetensors.index.json

@@ -0,0 +1,910 @@
+{
+  "metadata": {
+    "total_size": 6098479104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

quantization_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "autoround_version": "0.5.1",
+  "quant_method": "awq",
+  "zero_point": false,
+  "version": "gemm",
+  "modules_to_not_convert": [
+    "lm_head"
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d5fd6d2f8cf1172ac86cf982e2b88fa6732366b44dc1a32349379a54a6a044
+size 11423346

tokenizer_config.json

@@ -0,0 +1,242 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151670": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}