Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: mlx-community/Qwen2.5-Coder-7B-Instruct-4bit
+tags:
+  - mlx
+  - lora
+  - qwen
+  - commit-message
+  - conventional-commits
+  - git
+  - chinese
+---
+
+# git-ai-commit-sft
+
+A LoRA adapter fine-tuned on Qwen2.5-Coder-7B-Instruct-4bit to generate **Chinese Conventional Commits** commit messages from git diffs.
+
+Built for [git-ai-commit](https://github.com/your-org/git-ai-commit), an IntelliJ plugin that uses LLMs to generate commit messages.
+
+## Model
+
+- **Base model:** [mlx-community/Qwen2.5-Coder-7B-Instruct-4bit](https://huggingface.co/mlx-community/Qwen2.5-Coder-7B-Instruct-4bit)
+- **Fine-tuning:** LoRA (rank 8, 16 layers, 11.5M trainable params)
+- **Format:** MLX adapter (safetensors)
+
+## Training Data
+
+548 high-quality commit messages from two real-world repositories (one Java backend, one Go microservice), filtered to Chinese-only Conventional Commits format. Each training sample pairs a git diff (processed through the plugin's exact runtime pipeline — GitDiffFilter + PromptBuilder) with the corresponding human-written commit message.
+
+## Evaluation
+
+| Metric | Before | After |
+|---|---|---|
+| Conventional Commits rate | 96% | **100%** |
+| Chinese rate | 100% | 100% |
+| Single-line rate | 100% | 100% |
+| Mean similarity to reference | 0.339 | **0.546** |
+| Mean output length | 51 chars | 27 chars |
+
+## Usage
+
+```bash
+# Install mlx-lm
+pip install mlx-lm
+
+# Download and load
+python -m mlx_lm.generate \
+  --model mlx-community/Qwen2.5-Coder-7B-Instruct-4bit \
+  --adapter-path yisuiban/git-ai-commit-sft \
+  --prompt "你是一位资深工程师，擅长根据 git diff 生成一句中文提交信息。..."
+```
+
+From Python:
+
+```python
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+
+model, tokenizer = load(
+    "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit",
+    adapter_path="yisuiban/git-ai-commit-sft"
+)
+
+prompt = tokenizer.apply_chat_template(
+    [{"role": "user", "content": "你的提示词..."}],
+    tokenize=False, add_generation_prompt=True
+)
+response = generate(model, tokenizer, prompt=prompt, max_tokens=64,
+                    sampler=make_sampler(temp=0.0))
+```
+
+For Ollama deployment, see the [training repository](https://github.com/your-org/git-ai-commit-sft) for the full Modelfile and export pipeline.
+
+## Training Details
+
+- **Hardware:** Apple M1 Max (64GB unified memory)
+- **Framework:** MLX LoRA (mlx-lm 0.31.3)
+- **Optimizer:** Adam, learning rate 1e-5
+- **Batch:** 1 × gradient accumulation 8 (effective batch 8)
+- **Steps:** 250 (~4 epochs over 473 training samples)
+- **Max sequence length:** 4096 tokens
+- **Training time:** ~20 minutes on M1 Max

adapter_config.json

@@ -0,0 +1,41 @@
+{
+    "adapter_path": "adapters/qwen25-coder-7b-sft",
+    "batch_size": 1,
+    "clear_cache_threshold": 0,
+    "config": "configs/train.json",
+    "data": "data",
+    "fine_tune_type": "lora",
+    "grad_accumulation_steps": 8,
+    "grad_checkpoint": false,
+    "iters": 250,
+    "learning_rate": 1e-05,
+    "lora_parameters": {
+        "rank": 8,
+        "dropout": 0.0,
+        "scale": 20.0
+    },
+    "lr_schedule": null,
+    "mask_prompt": true,
+    "max_seq_length": 4096,
+    "model": "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit",
+    "num_layers": 16,
+    "optimizer": "adam",
+    "optimizer_config": {
+        "adam": {},
+        "adamw": {},
+        "muon": {},
+        "sgd": {},
+        "adafactor": {}
+    },
+    "project_name": null,
+    "report_to": null,
+    "resume_adapter_file": null,
+    "save_every": 100,
+    "seed": 42,
+    "steps_per_eval": 25,
+    "steps_per_report": 10,
+    "test": false,
+    "test_batches": 500,
+    "train": true,
+    "val_batches": 10
+}

adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4b49bef517767fbf4903c328eb989590fee1da89e6c50e031f42c289bb340e
+size 46161566