acon96/Home-Assistant-Requests
Viewer โข Updated โข 35.8k โข 464 โข 48
How to use firefox42/Llama3-Home-8b with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf firefox42/Llama3-Home-8b:F16 # Run inference directly in the terminal: llama cli -hf firefox42/Llama3-Home-8b:F16
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf firefox42/Llama3-Home-8b:F16 # Run inference directly in the terminal: llama cli -hf firefox42/Llama3-Home-8b:F16
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf firefox42/Llama3-Home-8b:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf firefox42/Llama3-Home-8b:F16
docker model run hf.co/firefox42/Llama3-Home-8b:F16
How to use firefox42/Llama3-Home-8b with Ollama:
ollama run hf.co/firefox42/Llama3-Home-8b:F16
How to use firefox42/Llama3-Home-8b with Docker Model Runner:
docker model run hf.co/firefox42/Llama3-Home-8b:F16
How to use firefox42/Llama3-Home-8b with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull firefox42/Llama3-Home-8b:F16
lemonade run user.Llama3-Home-8b-F16
lemonade list
Llama 3 8B trained on https://huggingface.co/datasets/acon96/Home-Assistant-Requests using unsloth
8-bit
16-bit