NVIDIA-NeMo / NVIDIA-NeMo/Gym

Unsloth multi-step integration

Open
#640 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

training
Dominant language
Python
Stars
1.2k
Forks
349
Avg merge
1d 21h
Merged PRs (30d)
318

Description

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.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the open TRL PR mentioned in the issue and how Unsloth's GRPOTrainer supports custom rollout functions. Determine the integration points needed for multi-step NeMo Gym environments, then verify that the environments can run through the supported rollout path once the TRL change is available.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.