ml-explore / ml-explore/mlx-examples

CLIP Tokenizer unable to take text of unequal length (or token length)

Open
#787 7 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9k
Forks
1.2k
PR merge metrics
No merged PRs in 30d

Description

this is about clip/tokenizer.py

The example:

tokenizer(["a photo of a cat", "a photo of a dog"])

only works 'cos they have exact same # of tokens. this one will fail:

tokenizer(["hello world", "how you doing?"])

ValueError: Initialization encountered non-uniform length.

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 in clip/tokenizer.py and reproduce the failure with the two example input lists from the issue. Trace how token lengths are handled, then verify that inputs with unequal token lengths are accepted while the existing equal-length example still works.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.