MY-GGUF
Collection
11 items • Updated
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?"
}
]
)How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with llama.cpp:
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
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
# 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
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
docker model run hf.co/joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with vLLM:
# 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?"
}
]
}'docker model run hf.co/joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
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
How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Unsloth Studio:
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
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
# 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
How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Pi:
# 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
# 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"
}
]
}
}
}# Start Pi in your project directory: pi
How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Hermes Agent:
# 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
# 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
hermes
How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with OpenClaw:
# 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
# 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
openclaw agent --local --agent main --message "Hello from Hugging Face"
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
How to use joongi007/ko-llama-3.1-5b-instruct-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull joongi007/ko-llama-3.1-5b-instruct-GGUF:Q4_K_M
lemonade run user.ko-llama-3.1-5b-instruct-GGUF-Q4_K_M
lemonade list
# 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:" \
--custom-provider-id llama-cpp \
--custom-compatibility openai \
--custom-text-input \
--accept-risk \
--skip-healthopenclaw agent --local --agent main --message "Hello from Hugging Face"<|start_header_id|>system<|end_header_id|>
{System}
<|eot_id|><|start_header_id|>user<|end_header_id|>
{User}
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{Assistant}
Q4_K_M)
system : 당신은 한국어 ai 모델입니다.
user : 왜 살아야 하는지 철학적 측면에서 접근해봐
assistant : 살아야 하는 이유에 대한 질문은 매우 깊고 복잡한 문제로, 철학적 관점에서도 여러 가지 해석이 존재합니다. 여기 몇 가지 주요 논점을 소개하겠습니다.
1. **개인적 의미와 목표**: 각 개인의 삶에는 고유한 의미와 목표가 있습니다. 어떤 사람에게는 사랑과 관계가, 다른 사람은 직업적 성취나 개인적 성장, 혹은 인류 전체에 기여하는 것이 삶의 중요한 부분일 수 있습니다.
2. **생명과 죽음 사이의 경계**: 인간은 생명과 죽음 사이에서 살아가는 존재입니다. 어떤 사람들은 자신의 삶에서 의미를 찾는다면 그들이 목숨을 두고 살아야 할 수도 있으며, 이는 단순히 생물학적인 이유뿐만 아니라 철학적 관점에서도 중요한 문제로 다루어집니다.
3. **인류의 발전과 기여**: 인간은 인류의 발전에 기여할 수 있는 존재입니다. 그러므로 자신의 삶에서 이에 기여하는 것은 그 자체로 매우 중요한 일일 수 있습니다.
4. **삶의 의미와 목적**: 철학자들은 종종 "삶의 의미"나 "삶의 목적"을 탐구합니다. 어떤 사람들은 사랑이나 영혼의 안정, 혹은 인류의 발전에 기여하는 것이 삶의 중요한 요소로 간주될 수 있습니다.
이러한 논점들은 철학적 탐구에서 인간 존재의 의미와 목표를 이해하는 데 도움을 줄 수 있으며, 각 개인의 삶에서 무엇이 진정으로 중요하게 여겨지는지를 고민하게 할 것입니다.<|eom_id|>
Base model
kikikara/ko-llama-3.1-5b-instruct
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: