Update README.md

README.md

@@ -38,6 +38,8 @@ sentences = [
 
 tokenized_query = ViTokenizer.tokenize(query)
 tokenized_sentences = [ViTokenizer.tokenize(sent) for sent in sentences]
+
+tokenized_pairs = [[tokenized_query, sent] for sent in tokenized_sentences]
 ```
 
 ## Usage with sentence-transformers
@@ -45,22 +47,28 @@ tokenized_sentences = [ViTokenizer.tokenize(sent) for sent in sentences]
 ```python
 from sentence_transformers import CrossEncoder
 model = CrossEncoder('itdainb/vietnamese-cross-encoder', max_length=256)
-scores = model.predict([(tokenized_query, sent) for sent in tokenized_sentences])
+scores = model.predict(tokenized_pairs)
 ```
 
 ## Usage with transformers
 
 ```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
 import torch
 
 model = AutoModelForSequenceClassification.from_pretrained('itdainb/vietnamese-cross-encoder')
 tokenizer = AutoTokenizer.from_pretrained('itdainb/vietnamese-cross-encoder')
 
-features = tokenizer([[tokenized_query, sent] for sent in tokenized_sentences],  padding=True, truncation=True, return_tensors="pt")
+activation_fct = torch.nn.Identity()
+
+features = tokenizer(*tokenized_pairs, padding=True, truncation="longest_first", return_tensors="pt", max_length=tokenizer.config.max_length)
 
 model.eval()
 with torch.no_grad():
-    scores = model(**features).logits
+    model_predictions = self.model(**features, return_dict=True)
+    logits = activation_fct(model_predictions.logits)
+
+    scores = [score[0] for score in logits]
     print(scores)
 ```