Update app.py

app.py

@@ -12,11 +12,11 @@ import torch
 #     torch_dtype=torch.float16,  # Reduce memory usage
 # )
 
-from optimum.intel import OVModelForCausalLM
+from auto_gptq import AutoGPTQForCausalLM
 from transformers import AutoTokenizer
 
 model_name = "abhifdsdf/good_disease_8bit"
-model = OVModelForCausalLM.from_pretrained(model_name)
+model = AutoGPTQForCausalLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)