handler_v3

handler.py

@@ -53,7 +53,7 @@ class EndpointHandler:
         """
         try:
             logger.info("Processing new request")
-            logger.debug(f"Input data: {data}")
+            logger.info(f"Input data: {data}")
             
             messages = data.get("messages", [])
             if not messages:
@@ -65,18 +65,18 @@ class EndpointHandler:
             logger.info(f"Generation parameters: {gen_params}")
             
             # Apply the chat template
-            logger.debug("Applying chat template")
+            logger.info("Applying chat template")
             prompt = self.tokenizer.apply_chat_template(
                 messages,
                 tokenize=False,
                 add_generation_prompt=True
             )
-            logger.debug(f"Generated prompt: {prompt}")
+            logger.info(f"Generated prompt: {prompt}")
             
             # Tokenize the prompt
-            logger.debug("Tokenizing input")
+            logger.info("Tokenizing input")
             inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
-            logger.debug(f"Input shape: {inputs.input_ids.shape}")
+            logger.info(f"Input shape: {inputs.input_ids.shape}")
             
             # Generate response
             logger.info("Generating response")