gemma.yaml

config_file: |
    backend: llama-cpp
    context_size: 8192
    known_usecases:
        - chat
        - completion
    mmap: true
    stopwords:
        - <|im_end|>
        - <end_of_turn>
        - <start_of_turn>
    template:
        chat: |
            {{.Input }}
            <start_of_turn>model
        chat_message: |-
            <start_of_turn>{{if eq .RoleName "assistant" }}model{{else}}{{ .RoleName }}{{end}}
            {{ if .FunctionCall -}}
            {{ else if eq .RoleName "tool" -}}
            {{ end -}}
            {{ if .Content -}}
            {{.Content -}}
            {{ end -}}
            {{ if .FunctionCall -}}
            {{toJson .FunctionCall}}
            {{ end -}}<end_of_turn>
        completion: |
            {{.Input}}
        function: |
            <start_of_turn>system
            You have access to functions. If you decide to invoke any of the function(s),
            you MUST put it in the format of
            {"name": function name, "parameters": dictionary of argument name and its value}

            You SHOULD NOT include any other text in the response if you call a function
            {{range .Functions}}
            {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
            {{end}}
            <end_of_turn>
            {{.Input -}}
            <start_of_turn>model
name: gemma