embedded/models/mamba-chat.yaml

name: mamba-chat
backend: mamba
parameters:
  model: "havenhq/mamba-chat"

trimsuffix: 
- <|endoftext|>

# https://huggingface.co/HuggingFaceH4/zephyr-7b-beta/blob/main/tokenizer_config.json
#   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
template:
  chat_message: |
    {{if eq .RoleName "assistant"}}<|assistant|>{{else if eq .RoleName "system"}}<|system|>{{else if eq .RoleName "user"}}<|user|>{{end}}
    {{if .Content}}{{.Content}}{{end}}
    </s>
    
  chat: |
    {{.Input}}
    <|assistant|>
    
  completion: |
    {{.Input}}
usage: |
    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
      "model": "mamba-chat",
      "messages": [{"role": "user", "content": "how are you doing"}],
      "temperature": 0.7
    }'