7b590e5 1dc6c65 54d2e53 80c7d2e
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
--- 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: - "</s>" - "<unk>" - "### User:" queue: max_size: 16 concurrency_count: 1