name: gpt-3.5-turbo
context_size: 2048
f16: true
gpu_layers: 90
mmap: true
trimsuffix: 
- "\n"
parameters:
  model: huggingface://TheBloke/phi-2-GGUF/phi-2.Q8_0.gguf

template:
  chat: &template |-
    Instruct: {{.Input}}
    Output:
  completion: *template

usage: |
      To use this model, interact with the API (in another terminal) with curl for instance:
      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
          "model": "phi-2",
          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
      }'