Add model

README.md

@@ -0,0 +1,42 @@
+
+---
+license: mit
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+---
+[[Paper]](https://openreview.net/forum?id=e3scLKNiNg&noteId=e3scLKNiNg) [[GitHub]](https://github.com/fra31/perceptual-metrics)
+
+Robust perceptual metric, based on CLIP model `laion/CLIP-ViT-B-16-laion2B-s34B-b88K`
+
+Adversarially fine-tuned with TeCoA ([Mao et al. (2023)](https://arxiv.org/abs/2212.07016)) on ImageNet with infinity-norm and radius 4/255.
+
+Performance on the perceptual similarity task [NIGHTS](https://dreamsim-nights.github.io):
+```
+Clean     L-inf, eps=4/255     L2, eps=3
+91.9      79.4                 77.1
+```
+
+## Usage
+```python
+model, _, image_processor = open_clip.create_model_and_transforms('hf-hub:chs20/TeCoA4-ViT-B-16-laion2B-s34B-b88K')
+```
+
+## Citation
+If you find this model useful, please consider citing our papers:
+```bibtex
+@inproceedings{croce2024adversarially,
+  title={Adversarially Robust CLIP Models Induce Better (Robust) Perceptual Metrics},
+  author={Croce, Francesco and Schlarmann, Christian and Singh, Naman Deep and Hein, Matthias},
+  year={2024},
+  booktitle={{ICML Workshop on Foundation Models in the Wild}}
+}
+```
+
+```bibtex
+@inproceedings{schlarmann2024robustclip,
+    title={Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models}, 
+    author={Schlarmann, Christian and Singh, Naman Deep and Croce, Francesco and Hein, Matthias},
+    year={2024},
+    booktitle={{ICML}}
+}
+```

open_clip_config.json

@@ -0,0 +1,32 @@
+{
+  "model_cfg": {
+    "embed_dim": 512,
+    "vision_cfg": {
+      "image_size": 224,
+      "layers": 12,
+      "width": 768,
+      "patch_size": 16
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 512,
+      "heads": 8,
+      "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_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e687adcdbcc9694947b6bf590d768cf667eddf04a5800c511fa4ffded4c48510
+size 598516980

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94945ab57ac75cbac140ecbe33fbb150c568560dd275f04c101c0c050500511
+size 598599478

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}