Instructions to use Tavernari/git-commit-message with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tavernari/git-commit-message with Transformers:

# Use a pipeline as a high-level helper
# Warning: Pipeline type "summarization" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline

pipe = pipeline("summarization", model="Tavernari/git-commit-message")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Tavernari/git-commit-message", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Tavernari/git-commit-message 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 Tavernari/git-commit-message:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Tavernari/git-commit-message:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Tavernari/git-commit-message:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Tavernari/git-commit-message:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Tavernari/git-commit-message:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Tavernari/git-commit-message:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Tavernari/git-commit-message:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tavernari/git-commit-message:Q4_K_M

Use Docker

docker model run hf.co/Tavernari/git-commit-message:Q4_K_M

LM Studio
Jan
Ollama
How to use Tavernari/git-commit-message with Ollama:
```
ollama run hf.co/Tavernari/git-commit-message:Q4_K_M
```

Unsloth Studio

How to use Tavernari/git-commit-message with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Tavernari/git-commit-message to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Tavernari/git-commit-message to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Tavernari/git-commit-message to start chatting

How to use Tavernari/git-commit-message with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Tavernari/git-commit-message:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Tavernari/git-commit-message:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Tavernari/git-commit-message with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Tavernari/git-commit-message:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Tavernari/git-commit-message:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Tavernari/git-commit-message with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Tavernari/git-commit-message:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Tavernari/git-commit-message:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Tavernari/git-commit-message with Docker Model Runner:
```
docker model run hf.co/Tavernari/git-commit-message:Q4_K_M
```

Lemonade

How to use Tavernari/git-commit-message with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tavernari/git-commit-message:Q4_K_M

Run and chat with the model

lemonade run user.git-commit-message-Q4_K_M

List all available models

lemonade list

git-commit-message / README.md

Tavernari

Update README.md

7cf0f42 verified over 1 year ago

preview code

Raw

History Blame

5.59 kB

	---
	datasets:
	- Tavernari/git-commit-message-dt
	metrics:
	- accuracy
	pipeline_tag: summarization
	tags:
	- git
	- commit
	- message
	---
	# Git Commit Message Generator (Reasoning Version)

	Welcome to the Git Commit Message Generator—an AI-powered tool that turns your code diffs into clear, meaningful commit messages with detailed reasoning. Hosted on Hugging Face, this reasoning version not only provides a commit message but also explains the thought process behind it, making your commit history more transparent and informative.

	Note: This is the reasoning version of the Git Commit Message Generator. For other versions (e.g., Chain of Draft or standard), check out my [Ollama repository](https://ollama.com/tavernari/git-commit-message) for more details.

	Beta Status: This version is in beta. Your feedback is essential to refine it further!

	## Output Format

	The model outputs two main components wrapped in a structured format:

	1. Reasoning: A detailed breakdown of the changes in your diff and the logic behind the commit message.
	2. Commit Message: A concise summary of the changes, followed by a more detailed description.

	Example Output:

	```
	<reasoning>
	The diff shows changes in `WalletManagerView.swift`. The most significant changes are the
	addition of a new `@State` variable `monthlySpentGoal` and modifications to existing functions
	and state variables. The `monthlySpentGoal` is now used in various places, such as in the
	`onSave` closure and in the `hasChanges` function. The purpose of these changes is to add a new
	feature that allows users to set a monthly spending goal for their wallets, which can be
	updated and saved with other wallet information.

	The changes include:
	- Adding a new `@State` variable `monthlySpentGoal`.
	- Updating the `onSave` closure to include `monthlySpentGoal`.
	- Using `monthlySpentGoal` in the `hasChanges` function to determine if the wallet's spending
	goal has changed.
	- Adding a new section `WalletGoalSpentSection` that uses `monthlySpentGoal`.
	- Updating the `onSetAsMain` function to use `monthlySpentGoal`.
	</reasoning>
	Add monthly spending goal feature to WalletManagerView

	This commit adds a new `@State` variable `monthlySpentGoal` to the `WalletManagerView` and
	updates the `onSave` closure and related functions to include and use this variable. This
	feature allows users to set and save a monthly spending goal for their wallets, enhancing the
	wallet management functionality.
	```

	This format gives you both the "why" and the "what" of your commit, enhancing clarity and context.

	## Using the Model

	You can interact with the model in two ways:

	### 1. Web Interface
	- Go to the [Hugging Face Model Page](https://huggingface.co/Tavernari/git-commit-message).
	- Paste your git diff into the input box.
	- Click "Generate" to get the reasoning and commit message.

	### 2. API Integration
	- Use the Hugging Face Inference API to integrate the model into your workflows.
	- Example in Python:

	```python
	import requests

	API_URL = "https://api-inference.huggingface.co/models/Tavernari/git-commit-message"
	headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

	def query(payload):
	response = requests.post(API_URL, headers=headers, json=payload)
	return response.json()

	diff = """
	diff --git a/file1.py b/file1.py
	index 83db48f..bf2a9a2 100644
	--- a/file1.py
	+++ b/file1.py
	@@ -1,3 +1,4 @@
	def hello():
	print("Hello, world!")
	+ print("Welcome to AI commit messages!")
	"""
	output = query({"inputs": diff})
	print(output)
	```

	- Replace `YOUR_HF_TOKEN` with your Hugging Face API token. The response will include both reasoning and the commit message.

	## Tips for Best Results

	- Clear Diffs: Use small, focused diffs for more accurate messages.
	- Proper Formatting: Ensure your diff is well-formatted for the model to interpret it correctly.
	- Output Handling: When using the API, parse the response to separate reasoning and the commit message if needed.

	## Installing `git-gen-commit` (Optional)

	For a command-line experience, you can install the `git-gen-commit` script, which generates commit messages from your git diff.

	Disclaimer: The `git-gen-commit` script uses the Ollama API, not the Hugging Face model. Results may differ from this reasoning version. For more details, visit my [Ollama repository](https://ollama.com/tavernari/git-commit-message).

	### Installation (macOS/Linux)
	Run this command to install `git-gen-commit` globally:

	```bash
	sudo sh -c 'curl -L https://gist.githubusercontent.com/Tavernari/b88680e71c281cfcdd38f46bdb164fee/raw/git-gen-commit \
	-o /usr/local/bin/git-gen-commit && chmod +x /usr/local/bin/git-gen-commit'
	```

	### Usage
	Once installed, run:

	```bash
	git gen-commit
	```

	This will analyze your current git diff and generate a commit message via the Ollama API.

	## Feedback and Contributions

	This is a community-driven project, and your input helps it grow!

	- Feedback: Use the community tab to give us feedback.
	- Support: If you’d like to fuel this passion project, consider a donation: [Buy me a coffee ☕️](https://donate.stripe.com/14k3d8dFqfeI96E8ww).

	## Disclaimer

	This tool is still evolving. Please review generated messages for accuracy before committing.

	## Get in Touch

	I’d love to hear from you! Connect with me at:

	- [LinkedIn](https://www.linkedin.com/in/victorctavernari/)
	- [GitHub](https://github.com/Tavernari)
	- [Twitter](https://twitter.com/vituu)
	- Email: victortavernari+gitcommitmessage@gmail.com

	Let’s make AI-powered development even better together!