Update app.py

app.py

@@ -36,10 +36,9 @@ def run_model(report):
         "Krooz/placement-classification-mistral-7b-instruct-v1",
         low_cpu_mem_usage=True,
         torch_dtype=torch.float16,
-        load_in_4bit=True,
-        cache_dir = "~/.cache/huggingface/models"
+        load_in_4bit=True
     )
-    tokenizer = AutoTokenizer.from_pretrained("Krooz/placement-classification-mistral-7b-instruct-v1",cache_dir="~/.cache/huggingface/models")
+    tokenizer = AutoTokenizer.from_pretrained("Krooz/placement-classification-mistral-7b-instruct-v1")
     input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cpu()
     
     # inference