phi-2-chat-custom.yaml

name: phi-2-chat
mmap: true
parameters:
  model: huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf
gpu_layers: 2
template:
  chat_message: |
    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "user"}}user{{end}}
    {{if .Content}}{{.Content}}{{end}}
    <|im_end|>
  chat: |
    {{.Input}}
    <|im_start|>assistant
  completion: |
    {{.Input}}
context_size: 4096
f16: true
stopwords:
- <|im_end|>
- <dummy32000>
usage: |
      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
          "model": "phi-2-chat",
          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
      }'