Inferenceable
Collection
2 items โข Updated
How to use HyperMink/Phi-3-Mini with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf HyperMink/Phi-3-Mini:Q5_K_M # Run inference directly in the terminal: llama cli -hf HyperMink/Phi-3-Mini:Q5_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf HyperMink/Phi-3-Mini:Q5_K_M # Run inference directly in the terminal: llama cli -hf HyperMink/Phi-3-Mini:Q5_K_M
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 HyperMink/Phi-3-Mini:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf HyperMink/Phi-3-Mini:Q5_K_M
docker model run hf.co/HyperMink/Phi-3-Mini:Q5_K_M
How to use HyperMink/Phi-3-Mini with Ollama:
ollama run hf.co/HyperMink/Phi-3-Mini:Q5_K_M
How to use HyperMink/Phi-3-Mini with Docker Model Runner:
docker model run hf.co/HyperMink/Phi-3-Mini:Q5_K_M
How to use HyperMink/Phi-3-Mini with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull HyperMink/Phi-3-Mini:Q5_K_M
lemonade run user.Phi-3-Mini-Q5_K_M
lemonade list
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HyperMink/Phi-3-Mini:Q5_K_M# Run inference directly in the terminal:
llama cli -hf HyperMink/Phi-3-Mini:Q5_K_Mgit 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 HyperMink/Phi-3-Mini:Q5_K_M# Run inference directly in the terminal:
./build/bin/llama cli -hf HyperMink/Phi-3-Mini:Q5_K_Mdocker model run hf.co/HyperMink/Phi-3-Mini:Q5_K_M5-bit
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf HyperMink/Phi-3-Mini:Q5_K_M# Run inference directly in the terminal: llama cli -hf HyperMink/Phi-3-Mini:Q5_K_M