backend: llama-cpp context_size: 4096 f16: true threads: 6 gpu_layers: 35 mmap: true name: llava roles: user: "USER:" assistant: "ASSISTANT:" system: "SYSTEM:" parameters: model: ggml-model-q4_k.gguf temperature: 0.2 top_k: 40 top_p: 0.95 template: chat: chat-simple-llava mmproj: mmproj-model-f16.gguf prompt_templates: - name: "chat-simple-llava" content: | A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions. {{.Input}} ASSISTANT: