embedded/models/tinyllama-chat.yaml

name: tinyllama-chat
mmap: true
parameters:
  model: huggingface://TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF/tinyllama-1.1b-chat-v0.3.Q8_0.gguf
  temperature: 0.2
  top_k: 40
  seed: -1
  top_p: 0.95
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|>
gpu_layers: 90

usage: |
      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
          "model": "tinyllama-chat",
          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
      }'