Unsloth multi-step integration

[cmunley1]

Use cases, pain points, and background
Support multi-step nemo gym environments in Unsloth through custom rollout function supported in TRL/Unsloth's GRPOTrainer

PR on TRL is open and under review to add support for this.

[cmunley1]

should be supported now with https://huggingface.co/docs/trl/main/nemo_gym