| --- |
| license: mit |
| library_name: open_clip |
| pipeline_tag: zero-shot-image-classification |
| tags: |
| - clip |
| - open_clip |
| - multilingual |
| - southeast-asia |
| language: |
| - en |
| - id |
| - jv |
| - su |
| - ms |
| - th |
| - vi |
| - my |
| --- |
| |
| # SEA-CLIP-Tiny — English initialisation (e0) |
|
|
| The English CLIP-KD student checkpoint used to initialise every SEA-CLIP-Tiny run in |
| [SEA-CLIP-Tiny (ACCV 2026)](https://huggingface.co/collections/fassabilf/sea-clip-tiny-accv-2026-6ab15f4d6cf7d50e98d5117c). It is the *starting point*, not a trained SEA model: |
| no Southeast Asian data has been seen at this point. |
|
|
| ## Usage |
|
|
| ```python |
| import open_clip |
| |
| model, _, preprocess = open_clip.create_model_and_transforms('hf-hub:fassabilf/sea-clip-tiny-init') |
| tokenizer = open_clip.get_tokenizer('hf-hub:fassabilf/sea-clip-tiny-init') |
| ``` |
|
|
| ## Model |
|
|
| | | | |
| |---|---| |
| | Architecture | ViT-T/16 vision tower + 12-layer / 384-wide text tower, embed dim 512 | |
| | Tokenizer | CLIP BPE, vocab 49408, context length 77 | |
| | Parameters | 46.11M (5.62M vision + 40.49M text) | |
| | Training data | English CLIP-KD pretraining (no SEA data) | |
| | Teacher | — | |
|
|
| ## Reproduce |
|
|
| Training and evaluation code: [https://github.com/fassabilf/sea-clip-tiny](https://github.com/fassabilf/sea-clip-tiny). |
| The exact training configuration of this checkpoint is in `params.txt` in this repo. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{seacliptiny2026, |
| title = {SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages}, |
| booktitle = {Asian Conference on Computer Vision (ACCV)}, |
| year = {2026} |
| } |
| ``` |
|
|
