llama.cpp/tests/chat/goldens/Qwen-Qwen2.5-Math-7B-Instruct-tool_use.txt

57 lines
2.6 KiB
Plaintext

<|im_start|>system
Please reason step by step, and put your final answer within \boxed{}.
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{"type": "function", "function": {"name": "ipython", "description": "Runs code in an ipython interpreter and returns the result of the execution after 60 seconds.", "parameters": {"type": "object", "properties": {"code": {"type": "string", "description": "The code to run in the ipython interpreter."}}, "required": ["code"]}}}
{"type": "function", "function": {"name": "brave_search", "description": "Executes a web search with Brave.", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "The query to search for."}}, "required": ["query"]}}}
{"type": "function", "function": {"name": "wolfram_alpha", "description": "Executes a query with Wolfram Alpha.", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "The query to execute."}}, "required": ["query"]}}}
{"type": "function", "function": {"name": "test", "description": "Runs a test.", "parameters": {"type": "object", "properties": {"condition": {"type": "boolean", "description": "The condition to test."}}, "required": ["condition"]}}}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call><|im_end|>
<|im_start|>user
Print a hello world message with python.<|im_end|>
<|im_start|>assistant
<tool_call>
{"name": "ipython", "arguments": {"code": "print('Hello, World!')"}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
{"stdout": "Hello, World!"}
</tool_response><|im_end|>
<|im_start|>assistant
Anything else?<|im_end|>
<|im_start|>user
Test a tautology.<|im_end|>
<|im_start|>assistant
<tool_call>
{"name": "test", "arguments": {"condition": true}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
true
</tool_response><|im_end|>
<|im_start|>assistant
Truth is definitely true.<|im_end|>
<|im_start|>user
Check it on the web.<|im_end|>
<|im_start|>assistant
<tool_call>
{"name": "brave_search", "arguments": {"query": "what is truth anyway am I right?"}}
</tool_call><|im_end|>
<|im_start|>user
<tool_response>
{"title":"Truth: don't ask the web, ask an LLM instead!","url":"https://en.wikipedia.org/wiki/Truth"}
</tool_response><|im_end|>
<|im_start|>assistant
I don't need the web to answer you but I did check, as you asked. What now?<|im_end|>
<|im_start|>assistant