CohereForAI

/

c4ai-command-r-v01

like 1.07k

Follow

Cohere For AI 610

From the perspective of the model right now, after we do the second generation after the tool call to interpret the tool response, if we feed just that back into the chat history, it appears to the model that it hallucinated / generated it rather than doing a tool call.

Then when this happens a couple times the tool calling layer learns to stop calling tools and just calls respond every time and the model at that point (after a chat history where it appears to directly respond) is happy to hallucinate whatever.

In my mind, there is missing format template function for grounded tool use.

Thank you

I have the same question, do you have any solutions?