Add new SentenceTransformer model.

0_CLIPModel/CLIPModel.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016a1243bd9df5f1181668d35326d761f8da5b7d22f8ee1319973e37111c82a2
-size 605223903
+oid sha256:16afc66c29d22afa707a6118519bcb2d9fa56f07f4bb9cde21d87c9e5cf0283b
+size 605217061

README.md

@@ -4,11 +4,31 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
+- transformers
 ---
 
 # sentence-transformers/clip-ViT-B-32
 
-<!--- Describe your model here -->
+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.
+
+
 
 ## Usage (Sentence-Transformers)
 
@@ -29,20 +49,342 @@ embeddings = model.encode(sentences)
 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)
 
+
+
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): CLIPModel()
+  (0): CLIPModel(
+    (model): CLIP(
+      (visual): VisualTransformer(
+        (conv1): Conv2d(3, 768, kernel_size=(32, 32), stride=(32, 32), bias=False)
+        (ln_pre): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+        (transformer): Transformer(
+          (resblocks): Sequential(
+            (0): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (1): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (2): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (3): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (4): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (5): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (6): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (7): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (8): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (9): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (10): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+            (11): ResidualAttentionBlock(
+              (attn): MultiheadAttention(
+                (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
+              )
+              (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (mlp): Sequential(
+                (c_fc): Linear(in_features=768, out_features=3072, bias=True)
+                (gelu): QuickGELU()
+                (c_proj): Linear(in_features=3072, out_features=768, bias=True)
+              )
+              (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            )
+          )
+        )
+        (ln_post): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+      )
+      (transformer): Transformer(
+        (resblocks): Sequential(
+          (0): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (1): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (2): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (3): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (4): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (5): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (6): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (7): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (8): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (9): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (10): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+          (11): ResidualAttentionBlock(
+            (attn): MultiheadAttention(
+              (out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
+            )
+            (ln_1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+            (mlp): Sequential(
+              (c_fc): Linear(in_features=512, out_features=2048, bias=True)
+              (gelu): QuickGELU()
+              (c_proj): Linear(in_features=2048, out_features=512, bias=True)
+            )
+            (ln_2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+          )
+        )
+      )
+      (token_embedding): Embedding(49408, 512)
+      (ln_final): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
+    )
+  )
 )
 ```
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->
-
+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",
+}
+```

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
     "sentence_transformers": "2.0.0",
-    "transformers": "4.6.1",
-    "pytorch": "1.8.0"
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
   }
 }