Update app.py

app.py

@@ -1,5 +1,5 @@
 import transformers
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 from transformers import pipeline
 import gradio as gr
@@ -7,7 +7,7 @@ import gradio as gr
 llama_model = "meta-llama/Llama-2-7b-chat-hf"
 access_token = "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"
 
-model = AutoModel.from_pretrained(llama_model, token=access_token)
+model = AutoModelForCausalLM.from_pretrained(llama_model, token=access_token)
 tokenizer = AutoTokenizer.from_pretrained(llama_model, token=access_token)
 
 pipeline = transformers.pipeline(