Instructions to use marzoukbaig14/committed-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marzoukbaig14/committed-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="marzoukbaig14/committed-gguf",
	filename="committed-finetuned-Q4_K_M.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 marzoukbaig14/committed-gguf 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 marzoukbaig14/committed-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf marzoukbaig14/committed-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf marzoukbaig14/committed-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf marzoukbaig14/committed-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 marzoukbaig14/committed-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf marzoukbaig14/committed-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 marzoukbaig14/committed-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf marzoukbaig14/committed-gguf:Q4_K_M

Use Docker

docker model run hf.co/marzoukbaig14/committed-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use marzoukbaig14/committed-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "marzoukbaig14/committed-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marzoukbaig14/committed-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/marzoukbaig14/committed-gguf:Q4_K_M

Ollama
How to use marzoukbaig14/committed-gguf with Ollama:
```
ollama run hf.co/marzoukbaig14/committed-gguf:Q4_K_M
```

Unsloth Studio

How to use marzoukbaig14/committed-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 marzoukbaig14/committed-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 marzoukbaig14/committed-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for marzoukbaig14/committed-gguf to start chatting

How to use marzoukbaig14/committed-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marzoukbaig14/committed-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": "marzoukbaig14/committed-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use marzoukbaig14/committed-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf marzoukbaig14/committed-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 marzoukbaig14/committed-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use marzoukbaig14/committed-gguf with Docker Model Runner:
```
docker model run hf.co/marzoukbaig14/committed-gguf:Q4_K_M
```

Lemonade

How to use marzoukbaig14/committed-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull marzoukbaig14/committed-gguf:Q4_K_M

Run and chat with the model

lemonade run user.committed-gguf-Q4_K_M

List all available models

lemonade list

Committed — Qwen3-1.7B (Q4_K_M GGUF)

A small model fine-tuned to write Conventional Commits messages from a git diff. It runs locally on CPU via llama.cpp, so your code never leaves your machine.

This repo holds the merged, quantized GGUF used for serving. The training dataset, LoRA adapter, and source code are linked below.

Details

Base: Qwen/Qwen3-1.7B (Apache-2.0)
Method: QLoRA fine-tune, merged into the base, converted to GGUF
Quantization: Q4_K_M (~1.1 GB)
Task: single-file git diff to one Conventional Commits subject line, type(scope): description
Decoding: GBNF grammar-constrained, so output is always a well-formed CC line

Usage

The trained behavior depends on the exact prompt rendering used in training plus the GBNF grammar applied at decode time, so a bare llama-cpp-python prompt will not reproduce the evaluated output. Run it through the project's inference path instead.

Easiest — the CLI, which downloads this GGUF on first run and wires up the prompt + grammar for you:

pip install "committed @ git+https://github.com/marzoukbaig14/Committed.git" --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
git diff | committed

Or call it through the repo's engine.py, the FastAPI endpoint, or the Gradio Space — all linked below. Full instructions and options are in the repo README.

Results

Evaluated against the un-tuned Qwen3-1.7B base on a 442-example test set, scored by an LLM judge on four axes (judge validated against 50 hand-rated examples). Headline numbers reweighted to the true commit-type distribution.

Metric	Base	Fine-tuned
Type accuracy	0.131	0.637
Conjunctive pass-rate	0.181	0.471
Graded mean (0–3)	1.207	2.188
Faithfulness	0.43	0.86

The base model collapsed ~95% of outputs to feat regardless of the diff; fine-tuning fixed that. One axis (specificity) regressed slightly (0.81 → 0.71). Full breakdown, regression analysis, and curated sample outputs are in the eval writeup: FINDINGS_v1.md.

Live demo (browser) — try it on the portfolio site. Paste a diff, get a commit message.
Live demo (Gradio) — Hugging Face Space.
LoRA adapter — marzoukbaig14/committed-qwen3-1.7b-lora. The unmerged adapter weights, if you want to merge or train further.
Training dataset — marzoukbaig14/committed-train, filtered from CommitChronicle, with composition tables and provenance.
Source, training & eval code — github.com/marzoukbaig14/Committed.
Eval writeup — FINDINGS_v1.md. The honest before/after and regression analysis.

License

Apache-2.0, inherited from the Qwen3-1.7B base.

Downloads last month: 276

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for marzoukbaig14/committed-gguf

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(298)

this model

marzoukbaig14
/

committed-gguf