NVIDIA-NeMo / NVIDIA-NeMo/Gym

instruction_following environment quality verification

Open
#175 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

close-confirm-done 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
instruction_following resources server is currently unverified

Description:

Design:
May need to implement IFEval and IFBench inside Gym

Out of scope:

Acceptance Criteria:

  • A full W&B run where we see the IFEval and IFBench 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 instruction_following resources server and reviewing how environments and validation metrics are implemented in Gym. Then investigate the intended IFEval and IFBench integration points and the W&B run configuration. Done means a full W&B run shows meaningful improvement in both IFEval and IFBench validation accuracy.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, testing-qa
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.