Update app.py

app.py

@@ -46,8 +46,8 @@ h1 {
 }
 """
 
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, cache_dir="./cache")
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True, torch_dtype=torch.bfloat16, cache_dir="./cache").eval()
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True, torch_dtype=torch.bfloat16).eval()
 terminators = [tokenizer.eos_token_id]
 
 @spaces.GPU(duration=120)