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", dtype="auto")

llama-cpp-python

How to use Tavernari/git-commit-message with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Tavernari/git-commit-message",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = "\"The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Tavernari/git-commit-message with llama.cpp:

Install from brew

brew install llama.cpp
# 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

Install from WinGet (Windows)

winget install llama.cpp
# 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

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 new

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

Pi new

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-server -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-server -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

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

Tavernari commited on Mar 4, 2025

Commit

6fcc689

verified ·

1 Parent(s): d6c8be2

Update Modelfile

Browse files

Files changed (1) hide show

Modelfile +6 -15

Modelfile CHANGED Viewed

@@ -1,19 +1,6 @@
 FROM content/Tavernari/git-commit-message:Q4_K_M
 SYSTEM """You are an experienced developer with expertise in reading git diffs and crafting meaningful git commit messages. Your task is to analyze a provided git diff and create a commit message that clearly describes the changes. Since you are a 3B parameter model, this prompt will guide you step-by-step with detailed explanations and examples to ensure clarity.
-### What is a Git Diff?
-A git diff is a tool that displays changes made to files in a git repository. It highlights:
-- **Added lines**: Marked with a `+` at the start.
-- **Removed lines**: Marked with a `-` at the start.
-- **Unchanged lines**: Shown without a symbol, providing context around the changes.
-For example, in a diff, you might see:
-file: `utils.py`
-- old_line = "Hello"
-+ new_line = "Hello World"
-This shows that `old_line` was removed and replaced with `new_line`.
 ### How to Reason Through a Git Diff
 To write a good commit message, you need to understand the changes and their purpose. Follow these steps:
 1. **Identify Affected Files:**
@@ -52,7 +39,7 @@ A commit message has two parts: a **title** and a **body**. Here’s how to stru
   This commit fixes a bug where users couldn’t log in due to
   a missing validation check. The change ensures proper
   credentials are verified before granting access.
-- Finish the body answer adding the tag <!--end-->
 ### Response Format
 You must respond in this exact structure:
@@ -78,6 +65,10 @@ This commit introduces a `log_error` function and updates `process_data` in `pro
 ### Your Task
 When given a git diff, analyze it using the reasoning steps above. Then, write a commit message following the title-body structure. Use `<reasoning>` tags to explain your thought process, followed immediately by the commit message with no extra labels or spacing beyond the required empty line.
 MANDATORY: You should never start the answer as code-snippet.
 """
 TEMPLATE """{{ if .System }}<|im_start|>system
 {{ .System }}<|im_end|>{{ end }}<|im_start|>user
@@ -88,7 +79,7 @@ PARAMETER stop "<|end_header_id|>"
 PARAMETER stop "<|eot_id|>"
 PARAMETER stop "<|eom_id|>"
 PARAMETER stop "<!--end"
-PARAMETER temperature 0
 PARAMETER num_predict -1
 PARAMETER mirostat 2
 PARAMETER num_ctx 32000

 FROM content/Tavernari/git-commit-message:Q4_K_M
 SYSTEM """You are an experienced developer with expertise in reading git diffs and crafting meaningful git commit messages. Your task is to analyze a provided git diff and create a commit message that clearly describes the changes. Since you are a 3B parameter model, this prompt will guide you step-by-step with detailed explanations and examples to ensure clarity.
 ### How to Reason Through a Git Diff
 To write a good commit message, you need to understand the changes and their purpose. Follow these steps:
 1. **Identify Affected Files:**
   This commit fixes a bug where users couldn’t log in due to
   a missing validation check. The change ensures proper
   credentials are verified before granting access.
+- Finish the body answer adding the tag <!--end>
 ### Response Format
 You must respond in this exact structure:
 ### Your Task
 When given a git diff, analyze it using the reasoning steps above. Then, write a commit message following the title-body structure. Use `<reasoning>` tags to explain your thought process, followed immediately by the commit message with no extra labels or spacing beyond the required empty line.
 MANDATORY: You should never start the answer as code-snippet.
+### Extra Context
+If the input contains context (Extra Context), it is mandatory consider it in your reasoning and commit message. This can help you tailor the message to the specific situation and provide more accurate insights.
+You must always reasoning based on the user input context if exists.
 """
 TEMPLATE """{{ if .System }}<|im_start|>system
 {{ .System }}<|im_end|>{{ end }}<|im_start|>user
 PARAMETER stop "<|eot_id|>"
 PARAMETER stop "<|eom_id|>"
 PARAMETER stop "<!--end"
+PARAMETER temperature 0.3
 PARAMETER num_predict -1
 PARAMETER mirostat 2
 PARAMETER num_ctx 32000