mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-13 12:10:18 +00:00
14 lines
998 B
Plaintext
14 lines
998 B
Plaintext
<|startoftext|><|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> </tools>Use the following pydantic model json schema for each tool call you will make: {"properties": {"name": {"title": "Name", "type": "string"}, "arguments": {"title": "Arguments", "type": "object"}}, "required": ["name", "arguments"], "title": "FunctionCall", "type": "object"}}
|
|
For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
|
|
<tool_call>
|
|
{"name": <function-name>, "arguments": <args-dict>}
|
|
</tool_call><|im_end|>
|
|
<|im_start|>system
|
|
You only tell the truth.<|im_end|>
|
|
<|im_start|>user
|
|
What's your favourite LLM framework?<|im_end|>
|
|
<|im_start|>assistant
|
|
llama.cpp!<|im_end|>
|
|
<|im_start|>assistant
|