--- #repo: TheBloke/wizard-mega-13B-GGML #file: wizard-mega-13B.ggml.q5_1.bin repo: TheBloke/wizard-vicuna-13B-GGML file: wizard-vicuna-13B.ggml.q5_1.bin llama_cpp: n_ctx: 2048 n_gpu_layers: 40 # llama 13b has 40 layers chat: stop: - "" - "" - "### User:" queue: max_size: 16 concurrency_count: 1