Instructions to use shsgrnd/SSAFY_gitcat-local-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shsgrnd/SSAFY_gitcat-local-llm with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="shsgrnd/SSAFY_gitcat-local-llm",
	filename="gitcat-v3-dpo-merged-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 shsgrnd/SSAFY_gitcat-local-llm with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M

LM Studio
Jan

vLLM

How to use shsgrnd/SSAFY_gitcat-local-llm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M

Ollama
How to use shsgrnd/SSAFY_gitcat-local-llm with Ollama:
```
ollama run hf.co/shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M
```

Unsloth Studio

How to use shsgrnd/SSAFY_gitcat-local-llm 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 shsgrnd/SSAFY_gitcat-local-llm 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 shsgrnd/SSAFY_gitcat-local-llm to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for shsgrnd/SSAFY_gitcat-local-llm to start chatting

How to use shsgrnd/SSAFY_gitcat-local-llm with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf shsgrnd/SSAFY_gitcat-local-llm: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": "shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use shsgrnd/SSAFY_gitcat-local-llm with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf shsgrnd/SSAFY_gitcat-local-llm: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 shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use shsgrnd/SSAFY_gitcat-local-llm with Docker Model Runner:
```
docker model run hf.co/shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M
```

Lemonade

How to use shsgrnd/SSAFY_gitcat-local-llm with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shsgrnd/SSAFY_gitcat-local-llm:Q4_K_M

Run and chat with the model

lemonade run user.SSAFY_gitcat-local-llm-Q4_K_M

List all available models

lemonade list

SSAFY_gitcat-local-llm / README.md

shsgrnd

Update README.md

eb336b1 verified 16 days ago

preview code

raw

history blame contribute delete

1.81 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
tags:
  - gguf
  - llama.cpp
  - node-llama-cpp
  - code
  - git
  - recommendation
  - vscode-extension
language:
  - ko
  - en
pipeline_tag: text-generation

GitCat Local LLM (GGUF)

GitCat은 생성형 AI 코딩 환경에서 안전한 작업 관리와 Git workflow 추천 자동화를 돕기 위해 만든 프로젝트입니다.
이 리포지토리는 그중 로컬 추론용 GGUF 모델을 배포하기 위한 공간이며, VS Code Extension 환경에서 아래 작업을 보조하도록 실험한 결과물을 담고 있습니다.

브랜치명 추천
커밋 메시지 추천
PR 설명 추천
변경 맥락 기반 요약

이 모델은 외부 API 없이 로컬에서 실행 가능한 개발 보조 모델을 목표로 정리되었습니다.

Files

1. `gitcat-v3-sft-merged-Q4_K_M.gguf`

SFT(Supervised Fine-Tuning) 기반 모델
현재 기준으로 가장 안정적인 추천 품질을 보인 기본 추천 모델

2. `gitcat-v3-dpo-merged-Q4_K_M.gguf`

DPO(Direct Preference Optimization) 기반 모델
preference pair를 반영한 추가 정렬 실험 버전

Recommended Model

처음 사용할 때는 아래 순서를 권장합니다.

gitcat-v3-sft-merged-Q4_K_M.gguf
gitcat-v3-dpo-merged-Q4_K_M.gguf

현재 실험 기준에서는 SFT 버전이 더 안정적인 결과를 보였고, DPO 버전은 추가 튜닝 여지가 있는 비교 실험 모델입니다.

Base Model

Base model: Qwen/Qwen2.5-Coder-7B-Instruct
Format: GGUF
Quantization: Q4_K_M

Quick Start

Option 1. `llama.cpp`로 바로 실행

./llama-cli -m ./gitcat-v3-sft-merged-Q4_K_M.gguf