Libraries llama-cpp-python How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with llama-cpp-python:
# !pip install llama-cpp-python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="joongi007/ko-llama-3.1-5b-instruct-GGUF",
filename="ko-llama-3.1-5b-instruct-Q2_K.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 joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M Use Docker docker model run hf.co/joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M LM Studio Jan vLLM How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with vLLM:
Install from pip and serve model # Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "joongi007/ko-llama-3.1-5b-instruct-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": "joongi007/ko-llama-3.1-5b-instruct-GGUF",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}' Use Docker docker model run hf.co/joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M Ollama How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Ollama:
ollama run hf.co/joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M Unsloth Studio How to use joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-GGUF to start chatting Using HuggingFace Spaces for Unsloth # No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for joongi007/ko-llama-3.1-5b-instruct-GGUF to start chatting Pi How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Pi:
Start the llama.cpp server # Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf joongi007/ko-llama-3.1-5b-instruct-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": "joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M"
}
]
}
}
} Run Pi # Start Pi in your project directory:
pi Hermes Agent new How to use joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-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 joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M Run Hermes hermes Atomic Chat new OpenClaw new How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with OpenClaw:
Start the llama.cpp server # Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M 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 "joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M" \
--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 joongi007/ko-llama-3.1-5b-instruct-GGUF with Docker Model Runner:
docker model run hf.co/joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M Lemonade How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Lemonade:
Pull the model # Download Lemonade from https://lemonade-server.ai/
lemonade pull joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M Run and chat with the model lemonade run user.ko-llama-3.1-5b-instruct-GGUF-Q4_K_M List all available models lemonade list 
