Update myagent.py

myagent.py

@@ -60,7 +60,7 @@ class LocalLlamaModel:
         self.tokenizer = tokenizer
         self.device = 'cpu'
     
-    def generate(self, prompt: str, max_new_tokens=512, **kwargs):
+    def generate(self, prompt: str, max_new_tokens=512*5, **kwargs):
         try:
             # Generate answer using the provided prompt - following the recommended pattern
             # input_ids = self.tokenizer.apply_chat_template(
@@ -69,6 +69,9 @@ class LocalLlamaModel:
             #     return_tensors="pt",
             #     tokenize=True,
             # ).to(self.model.device)
+
+            print("Prompt: ", prompt)
+            print("Prompt type: ", type(prompt))
             
             inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)