NVIDIA-NeMo / NVIDIA-NeMo/Gym

Equivalence LLM Judge environment quality verification

Open
#166 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Use cases, pain points, and background
Equivallence LLM Judge resources server is currently unverified

Description:

Design:
May need to implement GPQA inside Gym

Out of scope:

Acceptance Criteria:

  • A full W&B run where we see the GPQA validation accuracy improve meaningfully

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 locating the Equivalence LLM Judge resources server and the GPQA integration point inside Gym. Review how a full W&B run measures GPQA validation accuracy. Done means the resources server is verified and a full W&B run shows a meaningful improvement in GPQA validation accuracy.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.