SEA-CLIP-Tiny release (ACCV 2026)

README.md

@@ -0,0 +1,59 @@
+---
+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}
+}
+```

open_clip_config.json

@@ -0,0 +1,32 @@
+{
+  "model_cfg": {
+    "embed_dim": 512,
+    "vision_cfg": {
+      "image_size": 224,
+      "layers": 12,
+      "width": 192,
+      "patch_size": 16
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 384,
+      "heads": 6,
+      "layers": 12
+    }
+  },
+  "preprocess_cfg": {
+    "mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "interpolation": "bicubic",
+    "resize_mode": "shortest"
+  }
+}

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e44bb81e1465b5ec2272f63ed30b2567a273c3470d300b41992731be476a7b5
+size 184564982