LAION-AI / LAION-AI/CLIP_benchmark
Evaluate mse aligned multilingual clip
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 814
- Forks
- 103
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/FreddeFrallan/Multilingual-CLIP
should be possible to add it simularly to https://github.com/LAION-AI/CLIP_benchmark/blob/main/clip_benchmark/models/japanese_clip.py
do you want to give it a try @FreddeFrallan ?
I'm still quite curious on how mse aligned mclip compared with the contrastive one
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 by reading clip_benchmark/models/japanese_clip.py and the linked Multilingual-CLIP project to understand the existing model integration pattern. Determine how the MSE-aligned model can be evaluated alongside the contrastive model; the work is done when it is available to the benchmark and the comparison can be run.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100