name: mixtral-instruct mmap: true parameters: model: huggingface://TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/mixtral-8x7b-instruct-v0.1.Q2_K.gguf temperature: 0.2 top_k: 40 seed: -1 top_p: 0.95 mirostat: 2 mirostat_eta: 1.0 mirostat_tau: 1.0 template: chat: &chat | [INST] {{.Input}} [/INST] completion: *chat context_size: 4096 f16: true gpu_layers: 90 usage: | curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{ "model": "mixtral-instruct", "prompt": "How are you doing?" }'