Update README.md

README.md

@@ -5,10 +5,13 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
-
+language:
+- bn
+metrics:
+- accuracy
 ---
 
-# {MODEL_NAME}
+# {shihab17/bangla-sentence-transformer }
 
 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.
 
@@ -26,9 +29,9 @@ Then you can use the model like this:
 
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+sentences = ['আমি আপেল খেতে পছন্দ করি। ', 'আমার একটি আপেল মোবাইল আছে।','আপনি কি এখানে কাছাকাছি থাকেন?', 'আশেপাশে কেউ আছেন?']
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('shihab17/bangla-sentence-transformer ')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -51,11 +54,11 @@ def mean_pooling(model_output, attention_mask):
 
 
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+sentences = ['আমি আপেল খেতে পছন্দ করি। ', 'আমার একটি আপেল মোবাইল আছে।','আপনি কি এখানে কাছাকাছি থাকেন?', 'আশেপাশে কেউ আছেন?']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained('shihab17/bangla-sentence-transformer')
+model = AutoModel.from_pretrained('shihab17/bangla-sentence-transformer')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -70,12 +73,32 @@ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']
 print("Sentence embeddings:")
 print(sentence_embeddings)
 ```
+## How to get sentence similarity
+
+```python
+from sentence_transformers import SentenceTransformer
+from sentence_transformers.util import pytorch_cos_sim
+
 
+transformer = SentenceTransformer('shihab17/bangla-sentence-transformer')
+
+sentences = ['আমি আপেল খেতে পছন্দ করি। ', 'আমার একটি আপেল মোবাইল আছে।','আপনি কি এখানে কাছাকাছি থাকেন?', 'আশেপাশে কেউ আছেন?']
+
+sentences_embeddings = transformer.encode(sentences)
+
+for i in range(len(sentences)):
+    for j in range(i, len(sentences)):
+        sen_1 = sentences[i]
+        sen_2 = sentences[j]
+        sim_score = float(pytorch_cos_sim(sentences_embeddings[i], sentences_embeddings[j]))
+        print(sen_1, '----->', sen_2, sim_score)
+```
 
 
 ## Evaluation Results
 
 <!--- Describe how your model was evaluated -->
+## Best MSE: 7.57528096437454
 
 For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})