Spaces:

ggml-org
/

gguf-my-repo

Running on A10G

gguf-my-repo / start.sh

reach-vb HF staff

Update start.sh (#81)

a5eaf96 verified 6 months ago

82 Bytes

	cd llama.cpp
	LLAMA_CUDA=1 make -j quantize gguf-split imatrix

	cd ..
	python app.py