docs: document the Gym to RL framework token-ID data interface#1554
Merged
ananthsub merged 2 commits intoJun 16, 2026
Merged
Conversation
ananthsub
added
documentation
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
bxyu-nvidia
approved these changes
Jun 10, 2026
Add a Data Interface section to the on-policy corrections page describing what token-ID fields the model server returns during training (prompt_token_ids, generation_token_ids, generation_log_probs), where they attach, and the rule that the message-level token IDs are the single source of truth: they are produced once by the model server and propagated turn-to-turn on the messages, and callers must not construct or inject prefix token IDs out of band. Signed-off-by: Ananth Subramaniam <ansubramania@nvidia.com>
ananthsub
force-pushed
the
ananthsub/docs-gym-rl-data-contract
branch
from
28f87d5 to
a60d730
Compare
|
🌿 Preview your docs: https://nvidia-preview-ananthsub-docs-gym-rl-data-contract.docs.buildwithfern.com/nemo/gym Here are the markdown pages you've updated: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow up to #1545
Add a Data Interface section to the on-policy corrections page describing what token ID fields the model server returns during training (
prompt_token_ids,generation_token_ids,generation_log_probs), where they attach, and the rule that the message-level token IDs are the single source of truth: they are produced once by the model server and propagated turn-to-turn on the messages, and callers must not construct or inject prefix token IDs out of band