updated

llama_models.py

@@ -1,5 +1,5 @@
 import os
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM # Ensure correct model class
+from transformers import AutoTokenizer, AutoModelForCausalLM # Ensure correct model class
 import aiohttp
 
 HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
@@ -11,7 +11,7 @@ def load_model(model_name):
  if not tokenizer or not model:
  print("Loading model and tokenizer...")
  tokenizer = AutoTokenizer.from_pretrained(model_name)
- model = AutoModelForSeq2SeqLM.from_pretrained(model_name) # Ensure correct model class
+ model = AutoModelForCausalLM.from_pretrained(model_name) # Ensure correct model class
  print("Model and tokenizer loaded successfully.")
  return tokenizer, model