Update handler.py

handler.py

@@ -2,7 +2,7 @@ import os
 from typing import Dict, List, Any
 from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
 import torch
-from peft import PeftModel
+from peft import PeftModel  # Import PeftModel
 from dotenv import load_dotenv
 
 load_dotenv()
@@ -12,6 +12,7 @@ class EndpointHandler:
         """
         Initializes the model and tokenizer.
         """
+        # Key settings (from environment variables, with defaults)
         max_seq_length = int(os.getenv("MAX_SEQ_LENGTH", 2048))
         max_new_tokens = int(os.getenv("MAX_NEW_TOKENS", 512))
         self.hf_token = os.getenv("HUGGINGFACE_TOKEN")