Update README.md

README.md

@@ -34,7 +34,8 @@ pipeline_tag: text-classification
 3. [Usage with `sentence-transformers`](#usage-with-sentence-transformers)
 4. [Usage with `transformers`](#usage-with-transformers)
 5. [Performance](#performance)
-6. [Citation](#citation)
+6. [Support me](#support-me)
+7. [Citation](#citation)
 
 
 ## Installation
@@ -100,14 +101,12 @@ model.half()
 
 features = tokenizer(tokenized_pairs, padding=True, truncation="longest_first", return_tensors="pt", max_length=MAX_LENGTH)
 
-activation_function = torch.nn.Sigmoid() if model.config.num_labels == 1 else torch.nn.Identity()
-
 model.eval()
 with torch.no_grad():
     model_predictions = model(**features, return_dict=True)
 
     logits = model_predictions.logits
-    logits = activation_function(logits)
+    logits = torch.nn.Sigmoid()(logits)
     scores = [logit[0] for logit in logits]
 
 # 0.9819, 0.2444, 0.9253
@@ -127,6 +126,16 @@ In the following table, we provide various pre-trained Cross-Encoders together w
 
  Note: Runtime was computed on a A100 GPU with fp16.
 
+## Support me
+If you find this work useful and would like to support its continued development, here are a few ways you can help:
+
+1. **Star the Repository**: If you appreciate this work, please give it a star. Your support encourages continued development and improvement.
+2. **Contribute**: Contributions are always welcome! You can help by reporting issues, submitting pull requests, or suggesting new features.
+3. **Share**: Share this project with your colleagues, friends, or community. The more people know about it, the more feedback and contributions it can attract.
+4. **Buy me a coffee**: If you’d like to provide financial support, consider making a donation. You can donate via
+   - Momo: 0948798843
+   - BIDV Bank: DAINB
+
 ## Citation
 
  Please cite as