Update README.md

README.md

@@ -53,7 +53,7 @@ input_tokenized = tokenizer.apply_chat_template(text_input, return_tensors="pt")
 output = model.generate(input_tokenized, max_new_tokens=18000)
 ```
 
-However, due to the extensive lengths of the benefit trees generated by BenefitReporter, we recommend using the [vllm](https://github.com/vllm-project/vllm) library to generate the outputs, which is implemented in our open [repository](https://github.com/jl3676/SafetyAnalyst).
+However, due to the extensive lengths of the benefit trees generated by BenefitReporter, **we recommend using the [vllm](https://github.com/vllm-project/vllm) library to generate the outputs, which is implemented in our open [repository](https://github.com/jl3676/SafetyAnalyst)**.
 
 ## Intended Uses of BenefitReporter