Update app.py

app.py

@@ -25,8 +25,8 @@ max_new_tokens = 2048
 print(f"Starting to load the model {model_name} into memory")
 
 tok = AutoTokenizer.from_pretrained(model_name)
-#m = AutoModelForCausalLM.from_pretrained(model_name).eval()
-m = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+m = AutoModelForCausalLM.from_pretrained(model_name).eval()
+#m = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
 print("m=====>device",m.device)
 # tok.convert_tokens_to_ids(["<|im_end|>", "<|endoftext|>"])
 stop_token_ids = [tok.eos_token_id]