backend: llama-cpp
context_size: 4096
f16: true

gpu_layers: 90
mmap: true
name: llava-1.6-vicuna

roles:
  user: "USER:"
  assistant: "ASSISTANT:"
  system: "SYSTEM:"

mmproj: mmproj-vicuna7b-f16.gguf
parameters:
  model: vicuna-7b-q5_k.gguf
  temperature: 0.2
  top_k: 40
  top_p: 0.95
  seed: -1

template:
  chat: |
    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:

download_files:
- filename: vicuna-7b-q5_k.gguf
  uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf
- filename: mmproj-vicuna7b-f16.gguf
  uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf

usage: |
    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
        "model": "llava-1.6-vicuna",
        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'