初始化项目，由ModelHub XC社区提供模型

Model: AviralGusain/unity-debug-coach
Source: Original Platform

.gitattributes

@@ -0,0 +1,42 @@
+*.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
+unity-debug-coach-Q4_K_M-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+unity-debug-coach-Q4_K_M-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+unity-debug-coach-Q4_K_M-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+unity-debug-coach-Q4_K_M-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+unity-debug-coach-Q4_K_M-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+unity-debug-coach-Q4_K_M-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,99 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+tags:
+- fine-tuned
+- unity
+- game-development
+- csharp
+- debugging
+- qlora
+- lora
+- unsloth
+- gguf
+datasets: []
+pipeline_tag: text-generation
+---
+
+# Unity C# Debugging Coach
+
+A fine-tuned language model that acts as a patient debugging coach for beginner and intermediate Unity game developers. Given a Unity/C# bug description, error message, or broken code snippet, the model responds with a structured four-part explanation: identify the problem, explain why it happens, provide a concrete fix, and add a prevention tip.
+
+## What this model does
+
+When given a Unity or C# debugging question, the model responds consistently in this structure:
+
+1. **Problem** — briefly identifies what is likely wrong
+2. **Why it happens** — explains the root cause in beginner-friendly language
+3. **How to fix it** — provides a concrete, actionable solution (often with corrected code)
+4. **Prevention tip** — gives a best-practice note to avoid the issue in future projects
+
+The model stays encouraging and practical, avoiding overly academic explanations.
+
+## Example usage
+
+**System prompt (recommended):**
+```
+You are a Unity C# debugging coach. When a student describes a bug or error, respond in four parts: (1) identify the problem, (2) explain why it happens, (3) give a concrete fix, (4) add a prevention tip. Keep your tone encouraging and your explanations beginner-friendly.
+```
+
+**Example input:**
+```
+My player keeps falling through the floor in my 2D platformer. I have a Rigidbody2D and a BoxCollider2D on the player, and a BoxCollider2D on the ground. No errors in the console.
+```
+
+**Example output:**
+```
+Problem:
+Your player is passing through the floor at runtime despite having the correct collider setup.
+
+Why it happens:
+This is almost always a collision detection issue. By default, Unity uses Discrete collision detection, which checks for collisions at each physics step. If your player moves fast enough (especially during a fall), it can teleport past a thin collider between steps — a problem called tunneling.
+
+How to fix it:
+Select your player's Rigidbody2D in the Inspector and change Collision Detection from "Discrete" to "Continuous". This tells Unity to check for collisions continuously along the movement path, preventing tunneling.
+
+Also verify:
+- Both colliders are active and not set as triggers
+- The ground layer is not excluded in the Physics 2D settings
+
+Prevention tip:
+Always use Continuous collision detection for fast-moving objects like players and projectiles. Reserve Discrete for slow or stationary objects to keep performance costs low.
+```
+
+## Training details
+
+| Detail | Value |
+|---|---|
+| Base model | `unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit` |
+| Fine-tuning method | QLoRA (LoRA r=16, alpha=32) |
+| Training examples | 600 |
+| Validation examples | 120 |
+| Epochs | 3 |
+| Max sequence length | 2048 tokens |
+| Learning rate | 2e-4 (cosine schedule) |
+| Batch size | 2 (grad accum 4, effective 8) |
+| Hardware | Colab A100 |
+| Framework | Unsloth + TRL SFTTrainer |
+
+## Dataset
+
+The training data was synthetically generated using GPT-5.2-chat via OpenRouter. Each example is a conversation pair where:
+
+- **User message:** A Unity/C# debugging question — ranging from short error-only reports to multi-line code snippets. Questions vary across 20 issue categories (NullReferenceException, collision bugs, NavMesh issues, animation transitions, etc.), 11 project contexts (2D platformer, RPG, top-down shooter, etc.), and 3 difficulty levels (beginner, intermediate, advanced beginner).
+- **Assistant message:** A structured response following the four-part format described above.
+
+## GGUF / LM Studio
+
+A Q4_K_M quantized GGUF is available in this repository for use in LM Studio, Ollama, or any llama.cpp-compatible runtime.
+
+To use in LM Studio: search for this repository by username in the model search.
+
+## Known limitations
+
+- The model was trained on synthetic data only; it has not seen real student conversations. Responses are structured and reliable, but may occasionally feel slightly formal compared to human tutor replies.
+- Coverage of very advanced Unity topics (custom render pipelines, DOTS/ECS, compute shaders) is limited — the training data focused on beginner/intermediate issues.
+- The model does not have access to live Unity documentation. For up-to-date API details, cross-reference with the official Unity Manual. As the teacher noted, RAG over Unity docs would significantly improve accuracy for version-specific questions.
+- Response quality may degrade on queries that mix multiple unrelated bugs in one message.

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

config.json

@@ -0,0 +1,62 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "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"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": 151665,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.4.6",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737feb93617e890307ab1545f50f9e92ea0ef989e884b02df019e8e7c19c0032
+size 1089994864

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334909cbd22374e6acd4669ca6874d586eb96dfba418ec37a8af5e5de7a9efd4
+size 932241128

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e5c1ffe79c8d198f56ae3e73a2ef474c20634b6f19a3a50a2b2223fd8719e4
+size 932233864

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3e5c9c6a8900580b9a0d5deae3f299d5cdf3d58ef99c9d30016305efeb9e4a
+size 932233864

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a554e9fa2ccde50d91d93868cc02125c7798876d4a3b50e142be8bc74f6756
+size 135790712

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23af75608160e3b6cadfd059b7ff83e4550d49de4bca2aef089575c207e70e5c
+size 855166128

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7344f572dc094786de6f7f81f4f04ed57b6a1eee128de12f917d58cb0964770
+size 932241152

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7d072ced37dc20c3f18d8bfc9e6e27c7369dc5d3db6fdd1f6e85e5477888c6
+size 932233888

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347e5576e72cf727f465549fc3b1ef66b49fdaa448d0b7f5073ddc19746e0975
+size 135790712

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a928f9f19d7225a5e0ac936fcbdba3cf70fa9cbdba990dbee4c55f5b9a07f98
+size 932233888

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4e40975af0bce6a2c86e791849d1921ec4190a3de55a9281fa178eeac09912
+size 932226608

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ec50cdccd845eb1cf372e0b420a0de1ad41b642e366dd95635888cad44ac67
+size 165159480

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9ccd0b5b36d4d07b65f865f96846a0767393c58e8655b330321001ed6fe3f1
+size 902865088

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8f3a3031fa43bab6da060fa403fe1341c38f79a85c467df89c7965b66bcfeb
+size 873510896

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebccc4061e05426f4d1589c5b3b68aeb280012fa0327a7b8c0de053d26ee52c
+size 932233888

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3ed99a06b3a8ec1c204acebff7f31f0be43589df833de67c566094e4b2d797
+size 194535536

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d74fe1c63ba464285957a917345d48b7f834822ae62b5da1e94e829d8d693c3
+size 932233888

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420e647adcba6843a33384d105153c25d9bd602ce8be063c58f29d16ff0d4e8c
+size 932233888

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f029323c8f4d76957544cdbaabd8b0075b8db37de0b0972a7f83fa016e5842d
+size 135790712

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4303bbcfd8aea9e5ab3dd7bd11762faf770017b1d1bdcc6178d74c6a343bd1
+size 330326216

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0b11bacdf6e014fe337caf3b2be2d5ae9aa4912e316aa5302063e3cd534ea5
+size 1089994848

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00021.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00021.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00021.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00021.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00021.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00021.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00007-of-00021.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00007-of-00021.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00008-of-00021.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00021.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00010-of-00021.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00010-of-00021.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00021.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00011-of-00021.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00011-of-00021.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00012-of-00021.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00012-of-00021.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00013-of-00021.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00013-of-00021.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00014-of-00021.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00014-of-00021.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00015-of-00021.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00015-of-00021.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00015-of-00021.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00016-of-00021.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00016-of-00021.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00017-of-00021.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00017-of-00021.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00017-of-00021.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00018-of-00021.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00018-of-00021.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00018-of-00021.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00020-of-00021.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.norm.weight": "model-00020-of-00021.safetensors",
+    "lm_head.weight": "model-00021-of-00021.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

unity-debug-coach-Q4_K_M-00001-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384e18067b4bd3b1fc4e06a3091a741db7025ab08f0edd146c59eae49b0fb7cd
+size 870500256

unity-debug-coach-Q4_K_M-00002-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a264cf5f45f0619fcffd08d6d15fa9ae1e9380c1191d5d68d5d8b76aa0a32f2a
+size 895488576

unity-debug-coach-Q4_K_M-00003-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279d8517d7b09753d75d27ecaebcb1c6cbac8cd634b6b534b9077277978fda21
+size 899168544

unity-debug-coach-Q4_K_M-00004-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd99b71c6e4dd0d682a45679898ccdbd69435cdae3bf837196fd6b26f285c22
+size 877984416

unity-debug-coach-Q4_K_M-00005-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a6858e920c295e44adb137226675d8d0f9e760caa23d047842bca0c6e356c3
+size 858726560

unity-debug-coach-Q4_K_M-00006-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20c5cd0b1199be4e5ea449c359ff1aa84d97a59520857e66e7a56f2aa31e558
+size 281205792