Replace clip model with transformers version

0_CLIPModel/config.json

@@ -1,4 +1,152 @@
 {
-  "model_name": "CLIPModel.pt",
-  "tokenizer_name": "bpe_simple_vocab_16e6.txt.gz"
-}
+  "_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
+}

0_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
+}

0_CLIPModel/{CLIPModel.pt → pytorch_model.bin}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16afc66c29d22afa707a6118519bcb2d9fa56f07f4bb9cde21d87c9e5cf0283b
-size 605217061
+oid sha256:a62934cf6216e42859223aed2df08b4f1bd0042cb31be80d2db5cd54f71c0d16
+size 605266175

0_CLIPModel/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|>"}

0_CLIPModel/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, "special_tokens_map_file": "/home/ukp-reimers/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5", "tokenizer_file": "/home/ukp-reimers/.cache/huggingface/transformers/7811def0c53be25ba790cb67ac785669b508a8d1cf8c912b8ac046c5f08aee68.c51a626c1dc62de865745e4ab7125f190823b458ac5ee9ce21b1d006512b3a53"}

README.md

@@ -1,18 +1,16 @@
 ---
 pipeline_tag: sentence-similarity
-license: apache-2.0
 tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
-- transformers
 ---
 
-# sentence-transformers/clip-ViT-B-32
-
-This the [OpenAI CLIP Model](https://github.com/openai/CLIP) ported to [sentence-transformers](https://www.SBERT.net) model: It maps images and text to a shared vector space.
+# {MODEL_NAME}
 
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a None dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
+<!--- Describe your model here -->
 
 ## Usage (Sentence-Transformers)
 
@@ -28,7 +26,7 @@ Then you can use the model like this:
 from sentence_transformers import SentenceTransformer
 sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('sentence-transformers/clip-ViT-B-32')
+model = SentenceTransformer('{MODEL_NAME}')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -37,39 +35,19 @@ print(embeddings)
 
 ## Evaluation Results
 
+<!--- Describe how your model was evaluated -->
 
-
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/clip-ViT-B-32)
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
 
 
 
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): CLIPModel(
-    (model): CLIP(
-      (visual): VisualTransformer()
-      (transformer): Transformer()
-      (token_embedding): Embedding(49408, 512)
-      (ln_final): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
-    )
-  )
+  (0): CLIPModel()
 )
 ```
 
 ## Citing & Authors
 
-This model was trained by [sentence-transformers](https://www.sbert.net/). 
-        
-If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
-```bibtex 
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "http://arxiv.org/abs/1908.10084",
-}
-```
+<!--- Describe where people can find more information -->

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
+    "transformers": "4.6.0",
+    "pytorch": "1.7.1"
   }
 }