LocalAI/gallery/llama3.1-reflective.yaml

---
name: "llama3-instruct"

config_file: |
  mmap: true
  cutstrings:
  - (.*?)</thinking>
  function:
    disable_no_action: true
    grammar:
      disable: true
    response_regex:
    - <function=(?P<name>\w+)>(?P<arguments>.*)</function>
  template:
    chat_message: |
      <|start_header_id|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}<|end_header_id|>

      {{ if .FunctionCall -}}
      Function call:
      {{ else if eq .RoleName "tool" -}}
      Function response:
      {{ end -}}
      {{ if .Content -}}
      {{.Content -}}
      {{ else if .FunctionCall -}}
      {{ toJson .FunctionCall -}}
      {{ end -}}
      <|eot_id|>
    function: |
      <|start_header_id|>system<|end_header_id|>

      You have access to the following functions:

      {{range .Functions}}
      Use the function '{{.Name}}' to '{{.Description}}'
      {{toJson .Parameters}}
      {{end}}

      Think very carefully before calling functions.
      If a you choose to call a function ONLY reply in the following format with no prefix or suffix:

      <function=example_function_name>{{`{{"example_name": "example_value"}}`}}</function>

      Reminder:
      - If looking for real time information use relevant functions before falling back to searching on internet
      - Function calls MUST follow the specified format, start with <function= and end with </function>
      - Required parameters MUST be specified
      - Only call one function at a time
      - Put the entire function call reply on one line
      <|eot_id|>
      {{.Input }}
      <|start_header_id|>assistant<|end_header_id|>
    chat: |
      {{.Input }}
      <|start_header_id|>assistant<|end_header_id|>
      <thinking>
    completion: |
      {{.Input}}
  context_size: 8192
  f16: true
  stopwords:
  - <|im_end|>
  - <dummy32000>
  - "<|eot_id|>"
  - <|end_of_text|>