embedded/models/llava-1.5.yaml

backend: llama-cpp
context_size: 4096
f16: true

gpu_layers: 90
mmap: true
name: llava-1.5

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

mmproj: llava-v1.5-7b-mmproj-Q8_0.gguf
parameters:
  model: llava-v1.5-7b-Q4_K.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-v1.5-7b-Q4_K.gguf
  uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-Q4_K.gguf
- filename: llava-v1.5-7b-mmproj-Q8_0.gguf
  uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-mmproj-Q8_0.gguf

usage: |
    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
        "model": "llava-1.5",
        "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}]}'