Instructions to use hks350d/git-diff-to-commit-gemma-3-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use hks350d/git-diff-to-commit-gemma-3-270m with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf hks350d/git-diff-to-commit-gemma-3-270m:Q8_0 # Run inference directly in the terminal: llama cli -hf hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hks350d/git-diff-to-commit-gemma-3-270m:Q8_0 # Run inference directly in the terminal: llama cli -hf hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf hks350d/git-diff-to-commit-gemma-3-270m:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
Use Docker
docker model run hf.co/hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use hks350d/git-diff-to-commit-gemma-3-270m with Ollama:
ollama run hf.co/hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use hks350d/git-diff-to-commit-gemma-3-270m with Docker Model Runner:
docker model run hf.co/hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
- Lemonade
How to use hks350d/git-diff-to-commit-gemma-3-270m with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hks350d/git-diff-to-commit-gemma-3-270m:Q8_0
Run and chat with the model
lemonade run user.git-diff-to-commit-gemma-3-270m-Q8_0
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Git Diff -> Commit Message (Gemma 3 270M IT + LoRA)
|
| 2 |
|
| 3 |
A small, fast model specialized to turn a git diff into a concise, English commit message. Built on top of `google/gemma-3-270m-it` and fine-tuned with LoRA using MLX on macOS.
|
|
@@ -150,4 +160,4 @@ The repository’s `format_commit_message_prompt` builds the correct prompt for
|
|
| 150 |
## License and credits
|
| 151 |
|
| 152 |
- Base model: Google Gemma 3 (`google/gemma-3-270m-it`). Use subject to the Gemma license terms.
|
| 153 |
-
- Fine-tuning code: MLX and utilities in this repository. See repository license for details.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
datasets:
|
| 4 |
+
- hks350d/commit-message-generation
|
| 5 |
+
- Maxscha/commitbench
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
base_model:
|
| 9 |
+
- google/gemma-3-270m-it
|
| 10 |
+
---
|
| 11 |
# Git Diff -> Commit Message (Gemma 3 270M IT + LoRA)
|
| 12 |
|
| 13 |
A small, fast model specialized to turn a git diff into a concise, English commit message. Built on top of `google/gemma-3-270m-it` and fine-tuned with LoRA using MLX on macOS.
|
|
|
|
| 160 |
## License and credits
|
| 161 |
|
| 162 |
- Base model: Google Gemma 3 (`google/gemma-3-270m-it`). Use subject to the Gemma license terms.
|
| 163 |
+
- Fine-tuning code: MLX and utilities in this repository. See repository license for details.
|