Update app.py

app.py

@@ -3,7 +3,7 @@ import uvicorn
 
 model_name = "TheBloke/Luna-AI-Llama2-Uncensored-GPTQ"
 
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig
+from transformers import AutoModel, AutoTokenizer, TextStreamer, BitsAndBytesConfig
 import torch
 
 bnb_config = BitsAndBytesConfig(
@@ -13,7 +13,7 @@ bnb_config = BitsAndBytesConfig(
 
 # Load model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
+model = AutoModel.from_pretrained(
     model_name,
     quantization_config=bnb_config,
     device_map="cpu",