google-research / google-research/t5x
Getting Logits of Tokens
Open
- Dominant language
- Python
- Stars
- 3k
- Forks
- 338
- PR merge metrics
- No merged PRs in 30d
Description
In inference, I want to get the logit over vocabulary for the first generated token. How can I do that?
Contributor guide
Research direction
No file, test, or entry point is named in the issue. Start by locating T5X’s inference entry points and determine whether they expose per-token vocabulary logits; done means a documented or supported way to retrieve the first generated token’s logits, verified with a focused inference check.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100