Upload 10 files

README.md

@@ -0,0 +1,48 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+---
+
+# clip-ViT-B-32
+
+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-B-32')
+
+#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 +1,152 @@
+{
+  "_name_or_path": "openai/clip-vit-base-patch32",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.6.0",
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": null,
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 32,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.6.0",
+    "use_bfloat16": false
+  },
+  "vision_config_dict": null
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.0",
+    "pytorch": "1.7.1"
+  }
+}

modules.json

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

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ddab2ac35ecdb346c38a57d9fd15f50cb53f395bb97014834b0d3d58f67c37
+size 134

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "do_lower_case": true, "name_or_path": "openai/clip-vit-base-patch32", "model_max_length": 77}