Update app.py

app.py

@@ -12,12 +12,10 @@ print('device =', device)
 model = AutoModelForCausalLM.from_pretrained(
     'Viet-Mistral/Vistral-7B-Chat',
     torch_dtype=torch.bfloat16, # change to torch.float16 if you're using V100
-    device_map="auto",
-    use_cache=True,
-    cache_dir='./hf_cache'
+    device_map="auto"
 )
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL, cache_dir='./hf_cache')
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
 
 # def generate_output(input_text:str,
 #                     top_p:float=0.95,