Add basic function calling example using a llama-cli python wrapper

[dmahurin]

• I have read the contributing guidelines
• Self-reported review complexity:
  • Low
  • Medium
  • High

This adds an example of function calling, by providing a python wrapper that creates a prompt with function definitions, and interprets the function calls in inference.

Example.

./examples/function-calling/llama-cli-function-runner.py  -m `huggingface-cli  download meetkai/functionary-small-v3.2-GGUF functionary-small-v3.2.Q4_0.gguf` -i --special
What is the weather in Phoenix?
Sure, I'll look that up for you. Let me just check the current weather conditions in Phoenix.>>>get_weather
{"location": "Phoenix"}<|eot_id|>
{"temperature": "30C"}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
The current weather in Phoenix is 30C.<|eot_id|>
What is 38484 + 323?
Sure, let's calculate that.>>>calculate
{"expression": "38484 + 323"}<|eot_id|>
{"result": 38807}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
The sum of 38484 and 323 is 38807.<|eot_id|>

[dmahurin]

This wrapper was superseded by #9639