NVIDIA-NeMo / NVIDIA-NeMo/Gym

feat: Support raw Chat Completions return for downstream SFT

Open
#540 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Use cases, pain points, and background
Gym is used for rollout collection on models to be used in downstream SFT. A lot of SFT training libraries don't support responses inputs, so Chat Completions schema is necessary

Description:
What should we do?

Design:
What files should be touched? What logic should be written?

Out of scope:
What are some items that this issue could be mistaken to cover that this issue should explicitly NOT cover?

Acceptance Criteria:

  • Individual items that need to be finished in order for this issue to be considered completed

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

The issue names rollout collection, Chat Completions, and downstream SFT, but provides no files, tests, or entry points. Start by locating the rollout response path and reviewing the downstream SFT schema requirements. Done should mean the issue has defined and implemented a raw Chat Completions return with explicit acceptance criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
18/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.