Status: Done

Some notes on Llama 3.2 tool calling that I found useful

Note: We recommend using Llama 70B-instruct or Llama 405B-instruct for applications that combine conversation and tool calling. Llama 8B-Instruct can not reliably maintain a conversation alongside tool calling definitions. It can be used for zero-shot tool calling, but tool instructions should be removed for regular conversations between the model and the user.

Flow diagram

https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1/

Meta Llama models can now output custom tool calls from a single message to allow easier tool calling. The following prompts provide an example of how custom tools can be called from the output of the model. It’s important to note that the model itself does not execute the calls; it provides structured output to facilitate calling by an executor. An example executor can be found in the llama-agentic-system. The tool format is similar to the OpenAI definition and can be adjusted to better suit your needs, as noted in the following section.