embedded/models/llava-1.6-mistral.yaml

backend: llama-cpp
context_size: 4096
f16: true

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

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

mmproj: llava-v1.6-7b-mmproj-f16.gguf
parameters:
  model: llava-v1.6-mistral-7b.gguf

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: llava-v1.6-mistral-7b.gguf
  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q6_K.gguf
- filename: llava-v1.6-7b-mmproj-f16.gguf
  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf

usage: |
    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
        "model": "llava-1.6-mistral",
        "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}]}'