Instructions to use seniruk/qwen2.5coder-0.5B_commit_msg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seniruk/qwen2.5coder-0.5B_commit_msg with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="seniruk/qwen2.5coder-0.5B_commit_msg",
	filename="qwen0.5-finetuned.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use seniruk/qwen2.5coder-0.5B_commit_msg 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 seniruk/qwen2.5coder-0.5B_commit_msg
# Run inference directly in the terminal:
llama cli -hf seniruk/qwen2.5coder-0.5B_commit_msg

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf seniruk/qwen2.5coder-0.5B_commit_msg
# Run inference directly in the terminal:
llama cli -hf seniruk/qwen2.5coder-0.5B_commit_msg

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 seniruk/qwen2.5coder-0.5B_commit_msg
# Run inference directly in the terminal:
./llama-cli -hf seniruk/qwen2.5coder-0.5B_commit_msg

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 seniruk/qwen2.5coder-0.5B_commit_msg
# Run inference directly in the terminal:
./build/bin/llama-cli -hf seniruk/qwen2.5coder-0.5B_commit_msg

Use Docker

docker model run hf.co/seniruk/qwen2.5coder-0.5B_commit_msg

LM Studio
Jan

vLLM

How to use seniruk/qwen2.5coder-0.5B_commit_msg with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "seniruk/qwen2.5coder-0.5B_commit_msg"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "seniruk/qwen2.5coder-0.5B_commit_msg",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/seniruk/qwen2.5coder-0.5B_commit_msg

Ollama
How to use seniruk/qwen2.5coder-0.5B_commit_msg with Ollama:
```
ollama run hf.co/seniruk/qwen2.5coder-0.5B_commit_msg
```

Unsloth Studio

How to use seniruk/qwen2.5coder-0.5B_commit_msg 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 seniruk/qwen2.5coder-0.5B_commit_msg 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 seniruk/qwen2.5coder-0.5B_commit_msg to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for seniruk/qwen2.5coder-0.5B_commit_msg to start chatting

How to use seniruk/qwen2.5coder-0.5B_commit_msg with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf seniruk/qwen2.5coder-0.5B_commit_msg

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": "seniruk/qwen2.5coder-0.5B_commit_msg"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use seniruk/qwen2.5coder-0.5B_commit_msg with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf seniruk/qwen2.5coder-0.5B_commit_msg

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 seniruk/qwen2.5coder-0.5B_commit_msg

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use seniruk/qwen2.5coder-0.5B_commit_msg with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf seniruk/qwen2.5coder-0.5B_commit_msg

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 "seniruk/qwen2.5coder-0.5B_commit_msg" \
  --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 seniruk/qwen2.5coder-0.5B_commit_msg with Docker Model Runner:
```
docker model run hf.co/seniruk/qwen2.5coder-0.5B_commit_msg
```

Lemonade

How to use seniruk/qwen2.5coder-0.5B_commit_msg with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull seniruk/qwen2.5coder-0.5B_commit_msg

Run and chat with the model

lemonade run user.qwen2.5coder-0.5B_commit_msg-{{QUANT_TAG}}

List all available models

lemonade list

seniruk commited on Nov 8, 2025

Commit

2b83545

verified ·

1 Parent(s): 54b6e4a

Delete app.py

Browse files

Files changed (1) hide show

app.py +0 -76

app.py DELETED Viewed

@@ -1,76 +0,0 @@
-import subprocess
-import gradio as gr
-# Paths
-BINARY_PATH = "./bin/llama-cli"        # prebuilt binary from zip
-MODEL_PATH = "./qwen0.5-finetuned.gguf"
-# Commit message prompt template
-commit_prompt = """Generate a meaningful commit message explaining all the changes in the provided Git diff.
-### Git Diff:
-{}
-### Commit Message:
-"""
-# Example git diff prefilled in Gradio
-git_diff_example = """
-diff --git a/index.html b/index.html
-index 89abcde..f123456 100644
---- a/index.html
-+++ b/index.html
-@@ -5,16 +5,6 @@ <body>
-     <h1>Welcome to My Page</h1>
--    <table border="1">
--        <tr>
--            <th>Name</th>
--            <th>Age</th>
--        </tr>
--        <tr>
--            <td>John Doe</td>
--            <td>30</td>
--        </tr>
--    </table>
-+    <p>This is a newly added paragraph replacing the table.</p>
- </body>
-</html>
-"""
-def generate_commit(git_diff: str, max_tokens: int = 64) -> str:
-    """Generate a commit message using the llama-cli binary."""
-    if not git_diff.strip():
-        return "Please provide a git diff to summarize."
-    prompt_text = commit_prompt.format(git_diff)
-    cmd = [
-        BINARY_PATH,
-        "-m", MODEL_PATH,
-        "-p", prompt_text,
-        "-n", str(max_tokens)
-    ]
-    try:
-        # Run the binary and capture output
-        result = subprocess.run(cmd, capture_output=True, text=True, check=True)
-        return result.stdout.strip()
-    except subprocess.CalledProcessError as e:
-        return f"Error running binary: {e}\n{e.stderr}"
-if __name__ == "__main__":
-    demo = gr.Interface(
-        fn=generate_commit,
-        inputs=[
-            gr.Textbox(lines=30, label="Git Diff", value=git_diff_example),
-            gr.Slider(1, 2048, value=64, step=1, label="max_tokens")
-        ],
-        outputs=gr.Textbox(label="Commit Message", lines=8),
-        title="Commit Message Generator",
-        description="Paste a git diff and generate a concise commit message using the GGUF model via llama-cli binary.",
-        allow_flagging="never"
-    )
-    demo.launch(share=False)