Spaces:

matthoffner
/

ggml-mllm

Paused

ggml-mllm / config.toml

Update config.toml

63bc36d almost 2 years ago

130 Bytes

	model="open_llama_7b_700bt_ggml/ggml-model-q4_0.bin"
	use_mmap="True"
	use_mlock="True"
	n_threads="6"
	n_ctx="2048"
	n_gpu_layers="50"