Add new SentenceTransformer model.

README.md

@@ -5,12 +5,13 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
+- transformers
 
 ---
 
 # ditengm/bge-base-en-v1.5-fine-tuned_reels_1.1
 
-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.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 <!--- Describe your model here -->
 
@@ -35,6 +36,44 @@ print(embeddings)
 
 
 
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('ditengm/bge-base-en-v1.5-fine-tuned_reels_1.1')
+model = AutoModel.from_pretrained('ditengm/bge-base-en-v1.5-fine-tuned_reels_1.1')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
 ## Evaluation Results
 
 <!--- Describe how your model was evaluated -->
@@ -47,6 +86,7 @@ For an automated evaluation of this model, see the *Sentence Embeddings Benchmar
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 768, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
 )
 ```
 

modules.json

@@ -4,5 +4,11 @@
     "name": "0",
     "path": "",
     "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
   }
 ]