From f68299baef238e8eadf8bf070df6a137a1017f0f Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 16 Jun 2026 05:34:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: AviralGusain/unity-debug-coach Source: Original Platform --- .gitattributes | 42 +++ README.md | 99 ++++++ chat_template.jinja | 54 +++ config.json | 62 ++++ model-00001-of-00021.safetensors | 3 + model-00002-of-00021.safetensors | 3 + model-00003-of-00021.safetensors | 3 + model-00004-of-00021.safetensors | 3 + model-00005-of-00021.safetensors | 3 + model-00006-of-00021.safetensors | 3 + model-00007-of-00021.safetensors | 3 + model-00008-of-00021.safetensors | 3 + model-00009-of-00021.safetensors | 3 + model-00010-of-00021.safetensors | 3 + model-00011-of-00021.safetensors | 3 + model-00012-of-00021.safetensors | 3 + model-00013-of-00021.safetensors | 3 + model-00014-of-00021.safetensors | 3 + model-00015-of-00021.safetensors | 3 + model-00016-of-00021.safetensors | 3 + model-00017-of-00021.safetensors | 3 + model-00018-of-00021.safetensors | 3 + model-00019-of-00021.safetensors | 3 + model-00020-of-00021.safetensors | 3 + model-00021-of-00021.safetensors | 3 + model.safetensors.index.json | 346 +++++++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 17 + unity-debug-coach-Q4_K_M-00001-of-00006.gguf | 3 + unity-debug-coach-Q4_K_M-00002-of-00006.gguf | 3 + unity-debug-coach-Q4_K_M-00003-of-00006.gguf | 3 + unity-debug-coach-Q4_K_M-00004-of-00006.gguf | 3 + unity-debug-coach-Q4_K_M-00005-of-00006.gguf | 3 + unity-debug-coach-Q4_K_M-00006-of-00006.gguf | 3 + 34 files changed, 704 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 model-00001-of-00021.safetensors create mode 100644 model-00002-of-00021.safetensors create mode 100644 model-00003-of-00021.safetensors create mode 100644 model-00004-of-00021.safetensors create mode 100644 model-00005-of-00021.safetensors create mode 100644 model-00006-of-00021.safetensors create mode 100644 model-00007-of-00021.safetensors create mode 100644 model-00008-of-00021.safetensors create mode 100644 model-00009-of-00021.safetensors create mode 100644 model-00010-of-00021.safetensors create mode 100644 model-00011-of-00021.safetensors create mode 100644 model-00012-of-00021.safetensors create mode 100644 model-00013-of-00021.safetensors create mode 100644 model-00014-of-00021.safetensors create mode 100644 model-00015-of-00021.safetensors create mode 100644 model-00016-of-00021.safetensors create mode 100644 model-00017-of-00021.safetensors create mode 100644 model-00018-of-00021.safetensors create mode 100644 model-00019-of-00021.safetensors create mode 100644 model-00020-of-00021.safetensors create mode 100644 model-00021-of-00021.safetensors create mode 100644 model.safetensors.index.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 unity-debug-coach-Q4_K_M-00001-of-00006.gguf create mode 100644 unity-debug-coach-Q4_K_M-00002-of-00006.gguf create mode 100644 unity-debug-coach-Q4_K_M-00003-of-00006.gguf create mode 100644 unity-debug-coach-Q4_K_M-00004-of-00006.gguf create mode 100644 unity-debug-coach-Q4_K_M-00005-of-00006.gguf create mode 100644 unity-debug-coach-Q4_K_M-00006-of-00006.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0cc382f --- /dev/null +++ b/.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5444c61 --- /dev/null +++ b/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. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..9840d40 --- /dev/null +++ b/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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|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\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- 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 %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..f2699e2 --- /dev/null +++ b/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 +} \ No newline at end of file diff --git a/model-00001-of-00021.safetensors b/model-00001-of-00021.safetensors new file mode 100644 index 0000000..3feefff --- /dev/null +++ b/model-00001-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737feb93617e890307ab1545f50f9e92ea0ef989e884b02df019e8e7c19c0032 +size 1089994864 diff --git a/model-00002-of-00021.safetensors b/model-00002-of-00021.safetensors new file mode 100644 index 0000000..acd3418 --- /dev/null +++ b/model-00002-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:334909cbd22374e6acd4669ca6874d586eb96dfba418ec37a8af5e5de7a9efd4 +size 932241128 diff --git a/model-00003-of-00021.safetensors b/model-00003-of-00021.safetensors new file mode 100644 index 0000000..09f632b --- /dev/null +++ b/model-00003-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e5c1ffe79c8d198f56ae3e73a2ef474c20634b6f19a3a50a2b2223fd8719e4 +size 932233864 diff --git a/model-00004-of-00021.safetensors b/model-00004-of-00021.safetensors new file mode 100644 index 0000000..c59f013 --- /dev/null +++ b/model-00004-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3e5c9c6a8900580b9a0d5deae3f299d5cdf3d58ef99c9d30016305efeb9e4a +size 932233864 diff --git a/model-00005-of-00021.safetensors b/model-00005-of-00021.safetensors new file mode 100644 index 0000000..d803221 --- /dev/null +++ b/model-00005-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a554e9fa2ccde50d91d93868cc02125c7798876d4a3b50e142be8bc74f6756 +size 135790712 diff --git a/model-00006-of-00021.safetensors b/model-00006-of-00021.safetensors new file mode 100644 index 0000000..406e524 --- /dev/null +++ b/model-00006-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23af75608160e3b6cadfd059b7ff83e4550d49de4bca2aef089575c207e70e5c +size 855166128 diff --git a/model-00007-of-00021.safetensors b/model-00007-of-00021.safetensors new file mode 100644 index 0000000..212d0fb --- /dev/null +++ b/model-00007-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7344f572dc094786de6f7f81f4f04ed57b6a1eee128de12f917d58cb0964770 +size 932241152 diff --git a/model-00008-of-00021.safetensors b/model-00008-of-00021.safetensors new file mode 100644 index 0000000..7c789f1 --- /dev/null +++ b/model-00008-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7d072ced37dc20c3f18d8bfc9e6e27c7369dc5d3db6fdd1f6e85e5477888c6 +size 932233888 diff --git a/model-00009-of-00021.safetensors b/model-00009-of-00021.safetensors new file mode 100644 index 0000000..005da77 --- /dev/null +++ b/model-00009-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347e5576e72cf727f465549fc3b1ef66b49fdaa448d0b7f5073ddc19746e0975 +size 135790712 diff --git a/model-00010-of-00021.safetensors b/model-00010-of-00021.safetensors new file mode 100644 index 0000000..93569cf --- /dev/null +++ b/model-00010-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a928f9f19d7225a5e0ac936fcbdba3cf70fa9cbdba990dbee4c55f5b9a07f98 +size 932233888 diff --git a/model-00011-of-00021.safetensors b/model-00011-of-00021.safetensors new file mode 100644 index 0000000..7b6e3e0 --- /dev/null +++ b/model-00011-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4e40975af0bce6a2c86e791849d1921ec4190a3de55a9281fa178eeac09912 +size 932226608 diff --git a/model-00012-of-00021.safetensors b/model-00012-of-00021.safetensors new file mode 100644 index 0000000..87f7837 --- /dev/null +++ b/model-00012-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ec50cdccd845eb1cf372e0b420a0de1ad41b642e366dd95635888cad44ac67 +size 165159480 diff --git a/model-00013-of-00021.safetensors b/model-00013-of-00021.safetensors new file mode 100644 index 0000000..e9222d3 --- /dev/null +++ b/model-00013-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9ccd0b5b36d4d07b65f865f96846a0767393c58e8655b330321001ed6fe3f1 +size 902865088 diff --git a/model-00014-of-00021.safetensors b/model-00014-of-00021.safetensors new file mode 100644 index 0000000..8aaeb82 --- /dev/null +++ b/model-00014-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8f3a3031fa43bab6da060fa403fe1341c38f79a85c467df89c7965b66bcfeb +size 873510896 diff --git a/model-00015-of-00021.safetensors b/model-00015-of-00021.safetensors new file mode 100644 index 0000000..f9443d4 --- /dev/null +++ b/model-00015-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebccc4061e05426f4d1589c5b3b68aeb280012fa0327a7b8c0de053d26ee52c +size 932233888 diff --git a/model-00016-of-00021.safetensors b/model-00016-of-00021.safetensors new file mode 100644 index 0000000..31c8544 --- /dev/null +++ b/model-00016-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3ed99a06b3a8ec1c204acebff7f31f0be43589df833de67c566094e4b2d797 +size 194535536 diff --git a/model-00017-of-00021.safetensors b/model-00017-of-00021.safetensors new file mode 100644 index 0000000..cf0e285 --- /dev/null +++ b/model-00017-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d74fe1c63ba464285957a917345d48b7f834822ae62b5da1e94e829d8d693c3 +size 932233888 diff --git a/model-00018-of-00021.safetensors b/model-00018-of-00021.safetensors new file mode 100644 index 0000000..e713782 --- /dev/null +++ b/model-00018-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420e647adcba6843a33384d105153c25d9bd602ce8be063c58f29d16ff0d4e8c +size 932233888 diff --git a/model-00019-of-00021.safetensors b/model-00019-of-00021.safetensors new file mode 100644 index 0000000..63eee9a --- /dev/null +++ b/model-00019-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f029323c8f4d76957544cdbaabd8b0075b8db37de0b0972a7f83fa016e5842d +size 135790712 diff --git a/model-00020-of-00021.safetensors b/model-00020-of-00021.safetensors new file mode 100644 index 0000000..21433b5 --- /dev/null +++ b/model-00020-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4303bbcfd8aea9e5ab3dd7bd11762faf770017b1d1bdcc6178d74c6a343bd1 +size 330326216 diff --git a/model-00021-of-00021.safetensors b/model-00021-of-00021.safetensors new file mode 100644 index 0000000..8700fc9 --- /dev/null +++ b/model-00021-of-00021.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b0b11bacdf6e014fe337caf3b2be2d5ae9aa4912e316aa5302063e3cd534ea5 +size 1089994848 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ce47658 --- /dev/null +++ b/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" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5340d81 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..eb4636f --- /dev/null +++ b/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 XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|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\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\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\\n' }}\n {{- message.content }}\n {{- '\\n' }}\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" +} \ No newline at end of file diff --git a/unity-debug-coach-Q4_K_M-00001-of-00006.gguf b/unity-debug-coach-Q4_K_M-00001-of-00006.gguf new file mode 100644 index 0000000..db86dda --- /dev/null +++ b/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 diff --git a/unity-debug-coach-Q4_K_M-00002-of-00006.gguf b/unity-debug-coach-Q4_K_M-00002-of-00006.gguf new file mode 100644 index 0000000..ecfe5fc --- /dev/null +++ b/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 diff --git a/unity-debug-coach-Q4_K_M-00003-of-00006.gguf b/unity-debug-coach-Q4_K_M-00003-of-00006.gguf new file mode 100644 index 0000000..6ce8f5a --- /dev/null +++ b/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 diff --git a/unity-debug-coach-Q4_K_M-00004-of-00006.gguf b/unity-debug-coach-Q4_K_M-00004-of-00006.gguf new file mode 100644 index 0000000..eb0fdb4 --- /dev/null +++ b/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 diff --git a/unity-debug-coach-Q4_K_M-00005-of-00006.gguf b/unity-debug-coach-Q4_K_M-00005-of-00006.gguf new file mode 100644 index 0000000..734af14 --- /dev/null +++ b/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 diff --git a/unity-debug-coach-Q4_K_M-00006-of-00006.gguf b/unity-debug-coach-Q4_K_M-00006-of-00006.gguf new file mode 100644 index 0000000..99d933b --- /dev/null +++ b/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