update llama model

llama_models.py

@@ -20,8 +20,14 @@ def load_model(model_name):
     return tokenizer, model
 
 async def process_text_local(model_name, text):
+    print("Loading model and tokenizer...")
     tokenizer, model = load_model(model_name)
+    print("Encoding text...")
     inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)  # Set max_length to 512
+    print("Text encoded successfully.")
+    print("Generating output...")
     outputs = model.generate(**inputs, max_length=512)
+    print("Output generated successfully.")
     result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print("Output decoded successfully.")
     return result