Corrected typos in README

README.md

@@ -109,7 +109,7 @@ conversation_history = [
     "content": prompt
   }
 ]
-inputs = self.tokenizer.apply_chat_template(
+inputs = tokenizer.apply_chat_template(
     conversation=conversation_history,
     add_generation_prompt=True,
     tokenize=True,
@@ -118,7 +118,7 @@ inputs = self.tokenizer.apply_chat_template(
 ).to(model.device)
 
 outputs = model.generate(**inputs, max_new_tokens=2048)
-print(tokenizer.decode(outputs, skip_special_tokens=True))
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
 ```
 
 ## Training Details
@@ -145,7 +145,7 @@ In the original VeriFastScore pipeline, evidence is aggregated at the sentence l
 
 - **Training regime:** : bf16 mixed precision
 - **Optimizer**: AdamW
-- **Scheduler**: Cosine decay (optional placeholder)
+- **Scheduler**: Cosine decay
 - **Batch size**: 8 (effective)
 - **Epochs**: 10 (5+5)