model.yaml

name: llama-3.1
backend: transformers
parameters:
  model: fakezeta/Meta-Llama-3.1-8B-Instruct-ov-awq 
context_size: 8192
type: OVModelForCausalLM
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|>
  completion: |
    {{.Input}}