Add new SentenceTransformer model

README.md

@@ -0,0 +1,49 @@
+---
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+pipeline_tag: sentence-similarity
+---
+
+# clip-ViT-L-14
+
+This is the Image & Text model [CLIP](https://arxiv.org/abs/2103.00020), which maps text and images to a shared vector space. For applications of the models, have a look in our documentation [SBERT.net - Image Search](https://www.sbert.net/examples/applications/image-search/README.html)
+
+## Usage
+
+After installing [sentence-transformers](https://sbert.net) (`pip install sentence-transformers`), the usage of this model is easy:
+
+  
+```python
+from sentence_transformers import SentenceTransformer, util
+from PIL import Image
+
+#Load CLIP model
+model = SentenceTransformer('clip-ViT-L-14')
+
+#Encode an image:
+img_emb = model.encode(Image.open('two_dogs_in_snow.jpg'))
+
+#Encode text descriptions
+text_emb = model.encode(['Two dogs in the snow', 'A cat on a table', 'A picture of London at night'])
+
+#Compute cosine similarities 
+cos_scores = util.cos_sim(img_emb, text_emb)
+print(cos_scores)
+```
+
+See our [SBERT.net - Image Search](https://www.sbert.net/examples/applications/image-search/README.html) documentation for more examples how the model can be used for image search, zero-shot image classification, image clustering and image deduplication.
+
+## Performance
+
+In the following table we find the zero-shot ImageNet validation set accuracy:
+
+| Model | Top 1 Performance |
+| --- | :---: |
+| [clip-ViT-B-32](https://huggingface.co/sentence-transformers/clip-ViT-B-32) | 63.3 |
+| [clip-ViT-B-16](https://huggingface.co/sentence-transformers/clip-ViT-B-16) | 68.1 |
+| [clip-ViT-L-14](https://huggingface.co/sentence-transformers/clip-ViT-L-14) | 75.4 |
+
+For a multilingual version of the CLIP model for 50+ languages have a look at: [clip-ViT-B-32-multilingual-v1](https://huggingface.co/sentence-transformers/clip-ViT-B-32-multilingual-v1)

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/Users/mrloh/.cache/huggingface/hub/models--sentence-transformers--clip-ViT-L-14/snapshots/3b12140ad0f9750045e404f187cfccd04bcaf250/0_CLIPModel",
+  "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
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "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
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.2.1",
+    "transformers": "4.46.0",
+    "pytorch": "2.5.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d974e3760ed5e9deb912c9c811ef8edf25ca61152a4cf6bb4de785371f15aa
+size 1710537716

modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.CLIPModel"
+  }
+]

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "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
+  }
+}

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 +1,31 @@
+{
+  "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": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}