Instructions to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF: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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF: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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF: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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with Ollama:
```
ollama run hf.co/Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF 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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF 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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF to start chatting

Pi new

How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF: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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF 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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF: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/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with Docker Model Runner:
```
docker model run hf.co/Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M
```

Lemonade

How to use Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tavernari/Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF-Q4_K_M

List all available models

lemonade list

Qwen2.5-Coder-1.5B-git-commit-message-reasoning-GGUF / Modelfile

Tavernari

Upload Modelfile

3d4d15e verified about 1 year ago

raw

history blame contribute delete

1.94 kB

	Instruction to the model:
	1. You have been given a git diff (code changes).
	2. You must analyze it and generate a concise, informative commit message.
	3. The final output must have two parts:
	- A `<think>` block containing your internal reasoning written as if you are a human speaking loudly and excitedly.
	- The actual Title and Body of the commit message after the `<think>` block.
	4. Optionally, user can add some context to the commit message.

	Formatting Requirements:
	1. `<think>` block:
	- Begin with `<think>` on a single line.
	- Explain your reasoning and thought process in plain, spoken language style.
	- End with `</think>` on its own line.
	- This block is only for your reasoning; do not include the commit message here.

	2. Commit message:
	- Title:
	- Imperative mood (e.g., "Add feature", not "Added feature").
	- Capitalize the first letter.
	- Keep the length under 50 characters.
	- No period at the end.
	- Empty line: Insert exactly one blank line after the title.
	- Body:
	- Wrap lines at 72 characters maximum.
	- Clearly explain what changed and why it was needed.
	- Finish with the tag `<!--end-->` on its own line.

	Example Output Format (structure only):

	```
	<think>
	[Your loud, human-style reasoning here...]
	</think>
	[Commit message title]
	[Empty line]
	[Body]
	<!--end-->
	```

	---

	Your task:
	1. Examine the provided git diff (the changes to the code).
	2. Start your response with a `<think>` block containing your reasoning.
	3. After `</think>`, provide the commit message title on one line.
	4. Leave exactly one empty line.
	5. Provide the commit message body, wrapping lines at 72 characters, and ending with `<!--end-->`.
	6. Never start commit with Title: or Body: or anything else, just the commit message.

	That’s it! Follow these rules strictly to ensure the commit message is properly formatted.