Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2021 OpenAI
+Copyright (c) 2026 Bora Kargi, Arnas Uselis, Seong Joon Oh
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,97 @@
+---
+license: mit
+library_name: open_clip
+language:
+- en
+base_model: openai/clip-vit-base-patch32
+base_model_relation: finetune
+datasets:
+- kbora/CS-CLIP-Training
+- kbora/Half-Truths
+tags:
+- clip
+- image-text-retrieval
+- compositionality
+- arxiv:2602.23906
+---
+
+# CS-CLIP: Component-Supervised CLIP
+
+Model for **[Half-Truths Break Similarity-Based Retrieval](https://arxiv.org/abs/2602.23906)**, NeurIPS 2026.
+Bora Kargi, Arnas Uselis, Seong Joon Oh
+
+[Project page](https://kargibora.github.io/half-truths/) · [Code](https://github.com/kargibora/CS-CLIP) · [Evaluation data](https://huggingface.co/datasets/kbora/Half-Truths) · [Training annotations](https://huggingface.co/datasets/kbora/CS-CLIP-Training)
+
+CS-CLIP fine-tunes CLIP using entity/relation units and their matched foils to improve image–text retrieval when a caption contains a plausible but incorrect detail. Both encoders are fine-tuned; inference uses the standard dual encoder.
+
+## Use
+
+
+The ViT-B/32 checkpoint loads directly with OpenCLIP:
+
+```bash
+pip install 'open_clip_torch>=2.24,<3'
+```
+
+```python
+import open_clip
+import torch
+from PIL import Image
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model, preprocess = open_clip.create_model_from_pretrained(
+    "hf-hub:kbora/CS-CLIP", device=device
+)
+model.eval()
+tokenizer = open_clip.get_tokenizer("ViT-B-32")
+
+image = preprocess(Image.open("image.jpg").convert("RGB")).unsqueeze(0).to(device)
+captions = ["A dog runs on the grass.", "A dog runs on the grass beside a bicycle."]
+with torch.inference_mode():
+    image_features = model.encode_image(image, normalize=True)
+    text_features = model.encode_text(tokenizer(captions).to(device), normalize=True)
+    similarities = image_features @ text_features.T
+print(similarities[0].cpu().tolist())
+```
+
+Replace `image.jpg` and the captions with your own inputs. Scores are cosine similarities.
+
+## Checkpoint
+
+- Backbone: OpenAI CLIP ViT-B/32, fine-tuned on COCO images and the released CS-CLIP annotations.
+- Input: RGB images at 224 × 224; English text with a 77-token context window.
+- Output: 512-dimensional image and text embeddings.
+- Files: `open_clip_pytorch_model.bin` contains the encoder weights; `open_clip_config.json` defines the OpenCLIP architecture and image preprocessing.
+
+The checkpoint contains the paper's fine-tuned CLIP encoder weights and loads directly with OpenCLIP.
+
+## Evaluation
+
+Half-Truth accuracy (%) on the released, human-verified evaluation sets:
+
+| Model | COCO–Qwen | COCO–Mistral | CC3M–Qwen |
+|---|---:|---:|---:|
+| CLIP | 34.0 | 28.6 | 36.1 |
+| CS-CLIP | 76.4 | 67.2 | 66.2 |
+
+CS-CLIP achieves 57.8% average image-to-text accuracy across the paper's 16 compositional benchmarks. See the [repository](https://github.com/kargibora/CS-CLIP#evaluate-half-truths) for evaluation commands and metric definitions.
+
+## Scope and limitations
+
+The model is intended for research on image–text retrieval and compositional understanding. A similarity score does not establish that every detail in a caption is correct. Training foils are generated automatically and can be noisy. Fine-tuning also has a zero-shot classification trade-off: the paper reports an average of 59.9%, compared with 63.6% for pretrained CLIP.
+
+## License
+
+Released under the [MIT license](LICENSE). Generated training annotations are CC BY 4.0; source images and captions retain their original terms.
+
+## Citation
+
+```bibtex
+@inproceedings{kargi2026halftruths,
+  title={Half-Truths Break Similarity-Based Retrieval},
+  author={Kargi, Bora and Uselis, Arnas and Oh, Seong Joon},
+  booktitle={Advances in Neural Information Processing Systems},
+  year={2026},
+  url={https://arxiv.org/abs/2602.23906}
+}
+```

open_clip_config.json

@@ -0,0 +1,32 @@
+{
+  "model_cfg": {
+    "embed_dim": 512,
+    "vision_cfg": {
+      "image_size": 224,
+      "layers": 12,
+      "width": 768,
+      "patch_size": 32
+    },
+    "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_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f514e7650964fcf954f095e2413dabaadb89b17a36030249042b18cdba3ec75b
+size 605210595