Update README.md

README.md

@@ -26,8 +26,8 @@ def generate_response():
         message = [
            {'content': prompt, 'role': 'user'},
         ]
-        formatted_chat = tokenizer.apply_chat_template(conversation,tokenize=True,add_generation_prompt=True,return_tensors='pt').to(device)   
-        _ = model.generate(formatted_chat,streamer=streamer,use_cache=True,max_new_tokens=512,do_sample=True)
+        formatted_chat = tokenizer.apply_chat_template(message,tokenize=True,add_generation_prompt=True,return_tensors='pt').to(device)   
+        _ = model.generate(formatted_chat,streamer=streamer,use_cache=True,max_new_tokens=1024,do_sample=True)
 
 if __name__ == '__main__':
     device = 'cuda' if torch.cuda.is_available() else 'cpu'