LocalAI/embedded/models/hermes-2-pro-mistral.yaml

name: hermes-2-pro-mistral
mmap: true
parameters:
  model: huggingface://NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/Hermes-2-Pro-Mistral-7B.Q6_K.gguf

roles:
  assistant_function_call: assistant
  function: tool
template:
  chat_message: |
    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "function"}}{{.Role}}{{else if eq .RoleName "user"}}user{{end}}
    {{ if eq .RoleName "assistant_function_call" }}<tool_call>{{end}}
    {{ if eq .RoleName "function" }}<tool_result>{{end}}
    {{if .Content}}{{.Content}}{{end}}
    {{if .FunctionCall}}{{toJson .FunctionCall}}{{end}}
    {{ if eq .RoleName "assistant_function_call" }}</tool_call>{{end}}
    {{ if eq .RoleName "function" }}</tool_result>{{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>
usage: |
      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
          "model": "hermes-2-pro-mistral",
          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
      }'