Update app.py

app.py

@@ -5,7 +5,7 @@ from huggingface_hub import InferenceClient
 Copied from inference in colab notebook
 """
 
-from transformers import AutoModel, AutoTokenizer
+from transformers import AutoModel, AutoTokenizer , AutoModelForCausalLM
 import torch
 
 # Load model and tokenizer globally to avoid reloading for every request
@@ -15,7 +15,7 @@ model_path = "llama_lora_model_1"
 tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True, legacy=False)
 
 # Load model
-model = AutoModel.from_pretrained("Heit39/llama_lora_model_1")
+model = AutoModelForCausalLM.from_pretrained("Heit39/llama_lora_model_1")
 
 # Define the response function
 def respond(