make setup
make run
make build
Build llama.cpp locally:
./scripts/build-llama.shDownload a GGUF model from the Kitsune models release:
./scripts/download-model.sh
Or choose a model:
MODEL="qwen2.5-1.5b-instruct-q4_k_m.gguf" ./scripts/download-model.sh
Run
go run .