Increase max_new_tokens in generate method to 1000 for enhanced output capacity

medbot/model.py

@@ -30,7 +30,7 @@ class ModelManager:
                 device_map="auto"
             )
 
-    def generate(self, prompt, max_new_tokens=800, temperature=0.5, top_p=0.999):
+    def generate(self, prompt, max_new_tokens=1000, temperature=0.5, top_p=0.9):
         self.load()
         inputs = self.tokenizer(prompt, return_tensors="pt")
         if torch.cuda.is_available():