Gym
Gym copied to clipboard
Salesforce xlam-function-calling-60k resources server
function calling resources server based on https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k
This pull request requires additional validation before any workflows can run on NVIDIA's runners.
Pull request vetters can view their responsibilities here.
Contributors can view more details about this message here.
above is actually reward hacking by calling more and more tools, changing reward structure to exact match.