Upload fine-tuned CLIP-L checkpoint

README.md

@@ -0,0 +1,43 @@
+---
+license: mit
+base_model: openai/clip-vit-large-patch14
+tags:
+- clip
+- zero-shot-image-classification
+- vision
+- hierarcaps
+pipeline_tag: zero-shot-image-classification
+---
+
+# HierarCaps CLIP-L
+
+Fine-tuned CLIP-L (ViT-L/14) checkpoint from the paper **[Emergent Visual-Semantic Hierarchies in Image-Text Representations](https://arxiv.org/abs/2407.08521)** (ECCV 2024).
+
+- **Paper:** https://arxiv.org/abs/2407.08521
+- **Project page:** https://hierarcaps.github.io/
+- **Code:** https://github.com/TAU-VAILab/hierarcaps
+- **Base model:** [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)
+
+This model was fine-tuned on the HierarCaps dataset to induce an emergent visual-semantic hierarchy in CLIP's embedding space, enabling zero-shot hierarchical reasoning about specificity between images and texts.
+
+## Usage
+
+```python
+from transformers import CLIPModel, AutoProcessor
+
+model = CLIPModel.from_pretrained("malper/hierarcaps-clip-l")
+processor = AutoProcessor.from_pretrained("malper/hierarcaps-clip-l")
+```
+
+See the [official code repository](https://github.com/TAU-VAILab/hierarcaps) for training and evaluation scripts used with this checkpoint.
+
+## Citation
+
+```bibtex
+@InProceedings{alper2024hierarcaps,
+  author    = {Morris Alper and Hadar Averbuch-Elor},
+  title     = {Emergent Visual-Semantic Hierarchies in Image-Text Representations},
+  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
+  year      = {2024}
+}
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fd744bdc51ac61f4cb94eb71c5bc3585b4e732b33dc45ee28ce3f0686db07f
+size 1710669253

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}