google-research / google-research/t5x

Getting Logits of Tokens

Open
#425 2 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.