ml-explore / ml-explore/mlx-examples
CLIP Tokenizer unable to take text of unequal length (or token length)
Open
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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