NVIDIA-NeMo / NVIDIA-NeMo/Curator

Verify reward model support

Open
#822 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.8k
Forks
328
Avg merge
4d 5h
Merged PRs (30d)
30

Description

In https://github.com/NVIDIA-NeMo/Curator/pull/820, we removed the reward model section because the only reward model on build.nvidia.com (https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-reward) was causing issues with Curator complaining that it isn't a reward model.

Since query_reward_model is used a couple of other places in our repository, we should verify its usage and eventually add it back to the tutorial.

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 PR #820 and the repository's other uses of query_reward_model, then inspect the removed reward-model section in the tutorial. Done means confirming whether the linked NVIDIA model is compatible and restoring the tutorial only after reward model support is verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.