LocalAI/aio/cpu/text-to-text.yaml

name: gpt-4
mmap: true
parameters:
  model: huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q2_K.gguf

template:
  chat_message: |
    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
    {{- if .FunctionCall }}
    <tool_call>
    {{- else if eq .RoleName "tool" }}
    <tool_response>
    {{- end }}
    {{- if .Content}}
    {{.Content }}
    {{- end }}
    {{- if .FunctionCall}}
    {{toJson .FunctionCall}}
    {{- end }}
    {{- if .FunctionCall }}
    </tool_call>
    {{- else if eq .RoleName "tool" }}
    </tool_response>
    {{- end }}<|im_end|>
  # https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF#prompt-format-for-function-calling
  function: |
    <|im_start|>system
    You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
    <tools>
    {{range .Functions}}
    {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
    {{end}}
    </tools>
    Use the following pydantic model json schema for each tool call you will make:
    {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']}
    For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
    <tool_call>
    {'arguments': <args-dict>, 'name': <function-name>}
    </tool_call><|im_end|>
    {{.Input -}}
    <|im_start|>assistant
    <tool_call>
  chat: |
    {{.Input -}}
    <|im_start|>assistant
  completion: |
    {{.Input}}
context_size: 4096
f16: true
stopwords:
- <|im_end|>
- <dummy32000>
- "\n</tool_call>"
- "\n\n\n"
usage: |
      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
          "model": "gpt-4",
          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
      }'