Spaces:

ggml-org
/

gguf-my-repo

Running on A10G

gguf-my-repo / start.sh

reach-vb HF staff

Update start.sh (#90)

5f0f1b0 verified 5 months ago

100 Bytes

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

	cd ..
	python app.py