Update README.md

README.md

@@ -1,8 +1,99 @@
 ---
 tags:
 - clip
+- siglip
 library_name: open_clip
 pipeline_tag: zero-shot-image-classification
-license: mit
+license: apache-2.0
+datasets:
+- webli
 ---
 # Model card for ViT-SO400M-16-SigLIP-i18n-256
+
+A SigLIP (Sigmoid loss for Language-Image Pre-training) model trained on WebLI in multiple languages (i18n variant) w/ a multi-lingual tokenizer.
+
+This model has been converted to PyTorch from the original JAX checkpoints in [Big Vision](https://github.com/google-research/big_vision). These weights are usable in both OpenCLIP (image + text) and timm (image only).
+
+## Model Details
+- **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification.
+- **Original:** https://github.com/google-research/big_vision
+- **Dataset:** WebLI
+- **Papers:**
+  - Sigmoid loss for language image pre-training: https://arxiv.org/abs/2303.15343
+
+## Model Usage
+### With OpenCLIP
+```python
+import torch
+import torch.nn.functional as F
+from urllib.request import urlopen
+from PIL import Image
+from open_clip import create_model_from_pretrained, get_tokenizer # works on open-clip-torch>=2.27, timm>=1.0.10
+
+model, preprocess = create_model_from_pretrained('hf-hub:timm/ViT-SO400M-16-SigLIP-i18n-256')
+tokenizer = get_tokenizer('hf-hub:timm/ViT-SO400M-16-SigLIP-i18n-256')
+
+image = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+image = preprocess(image).unsqueeze(0)
+
+labels_list = ["a dog", "a cat", "a donut", "a beignet"]
+text = tokenizer(labels_list, context_length=model.context_length)
+
+with torch.no_grad(), torch.cuda.amp.autocast():
+    image_features = model.encode_image(image)
+    text_features = model.encode_text(text)
+    image_features = F.normalize(image_features, dim=-1)
+    text_features = F.normalize(text_features, dim=-1)
+
+    text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)
+
+zipped_list = list(zip(labels_list, [round(p.item(), 3) for p in text_probs[0]]))
+print("Label probabilities: ", zipped_list)
+```
+
+### With `timm` (for image embeddings)
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+image = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'vit_so400m_patch14_siglip_256.webli_i18n',
+    pretrained=True,
+    num_classes=0,
+)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(image).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
+```    
+
+## Citation
+```bibtex
+@article{zhai2023sigmoid,
+  title={Sigmoid loss for language image pre-training},
+  author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
+  journal={arXiv preprint arXiv:2303.15343},
+  year={2023}
+}
+```
+```bibtex
+@misc{big_vision,
+  author = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
+  title = {Big Vision},
+  year = {2022},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/google-research/big_vision}}
+}
+```
+