update Readme

README.md

@@ -5,11 +5,12 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
+- vietnamese
 ---
 
-# {MODEL_NAME}
+# {vietnamese-sbert}
 
-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.
+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 on Vietnamese language.
 
 <!--- Describe your model here -->
 
@@ -25,9 +26,9 @@ 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 = ["Cô giáo đang ăn kem", "Chị gái đang thử món thịt dê"]
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('keepitreal/vietnamese-sbert')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -50,11 +51,11 @@ def mean_pooling(model_output, attention_mask):
 
 
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+sentences = ['Cô giáo đang ăn kem', 'Chị gái đang thử món thịt dê']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained(''keepitreal/vietnamese-sbert')
+model = AutoModel.from_pretrained('keepitreal/vietnamese-sbert')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')