初始化项目，由ModelHub XC社区提供模型

Model: Yvthyvq/Liujgoj-Cantonese-Qwen3-8B-Instruct
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,16 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant."""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: Yvthyvq/cantonese-qwen3-8b-base
+tags:
+- cantonese
+- orthography
+- liujgoj
+- speech-first
+- sft
+- text-generation
+pipeline_tag: text-generation
+---
+# cantonese-qwen3-8b-instruct
+
+融入純粹粵語語音 manifold（語言流形）嘅多任務 Instruct 大模型。本模型基於 cantonese-qwen3-8b-base 進行深度大規模指令微調（SFT），專注於拉丁化粵語書寫系統 —— **Liujgoj 溜歌粵語**。
+
+透過將音素同語義對齊，本模型擺脫咗傳統漢字對粵語思維嘅束縛，為語音原生（Speech-native）AI 奠定強大嘅文本語意底座。
+
+---
+
+## 🚀 模型亮點
+
+* **純語音導向（Phonology-first）**：基於 Liujgoj 拉丁化正詞法（Tone-as-letter 字母表調法：j, r, x, q, h），繞過漢字表意限制，實現更高效嘅 AI 語意向量建模。
+* **強大數據錘煉**：精選超過多部經典香港電影對白、高頻粵語詞庫（約 13,000 詞），精心策劃超 14 萬行高質量多任務對話與指令對（Instruction pairs）進行全參數/大窗口微調。
+
+---
+
+## 🛠️ 快速部署與使用
+
+### 1. 使用 Hugging Face 官方最新 `hf` 工具下載
+
+由於模型採用最新 high-performance 傳輸架構，推薦使用最新 `hf` 工具進行下載（速度極快）：
+
+```bash
+export HF_XET_HIGH_PERFORMANCE=1
+hf download Yvthyvq/cantonese-qwen3-8b-instruct --local-dir ./cantonese-qwen3-8b-instruct
+
+---
+
+## 🚀 快速開始 / Quick Start
+
+### 1. 安裝與環境變量配置
+```bash
+export HF_XET_HIGH_PERFORMANCE=1
+export HF_ENDPOINT=[https://hf-mirror.com](https://hf-mirror.com)
+
+### 2. Python 檔案推演 (使用 Transformers 載入)
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Yvthyvq/cantonese-qwen3-8b-instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# 提示詞請盡量使用 Liujgoj 粵語拼寫或地道口語進行互動
+messages = [
+    {"role": "user", "content": "Neiq hour, neiq horyiq zouh dij mej?"} # 範例
+]
+
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 157089
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "5.6.0"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabf115425f6c92fd4d52445443c668330b492dc0f139cef6b9d8ca2eb85d8f8
+size 1286873216

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5b9b59716d1e81f586e4020b2eb3731caef5cc3f297b37f37c0a237bc772c4
+size 1983163296

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3c35b3b30211c04746d1531615a12462ac57e0f519478100edda6377491114
+size 1996580072

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a36c1f70f4b24811cdfed2c0bb157f2b3cc767dc34aaf15ec54774c1ef6670
+size 1937867664

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27393d934566b873484ee80b49cfec0ce451d96ab74d1f87a65e4af75649b7b
+size 1929470680

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9017a15fa74e22c6918cb14fd4aaac8431e799a171c1dbea46d69c236ba7895d
+size 1929470680

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ff61472ce8d0fe49f3ef10c058e9fa4468621d01c3938c746dc6f3911e327c
+size 1929470680

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae669783c9906ad47fdc1c677b13370f9643f466b0fbd9aca0316d6510b7db0
+size 1929470680

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982f74bd68d486de6752fcb185ef89620d3f9c8ba1848c232a99ed0dda60927c
+size 1543576520

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8232948736,
+    "total_size": 16465897472
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}