Update README.md

Fix typo in code example and DS size

README.md

@@ -48,7 +48,7 @@ BrowseSafe is based on the Qwen3-30B-A3B architecture.
 
 ## Performance
 
-We evaluated BrowseSafe on BrowseSafe-Bench, a realistic benchmark comprising 3,691 test samples of complex HTML payloads.
+We evaluated BrowseSafe on BrowseSafe-Bench, a realistic benchmark comprising 3,680 test samples of complex HTML payloads.
 
 | Model Name        | Config        | F1 Score | Precision | Recall | Balanced <br>Accuracy | Refusals |
 |-------------------|---------------|----------|-----------|--------|-----------------------|----------|
@@ -89,7 +89,7 @@ Below is a code snippet illustrating how to use BrowseSafe.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "perplexity-ai/browsesafe-bench"
+model_name = "perplexity-ai/browsesafe"
 
 # load the tokenizer and the model
 tokenizer = AutoTokenizer.from_pretrained(model_name)