Spaces:

matthoffner
/

ggml-mllm

Paused

ggml-mllm / config.toml

Update config.toml

fbb92ee almost 2 years ago

75 Bytes

	model="llama-2-13b-chat.ggmlv3.q4_K_M.bin"
	n_threads="4"
	n_gpu_layers="100"