Update app/model/model.py

app/model/model.py

@@ -23,10 +23,9 @@ class LLM:
         # Load model and tokenizer
         model = AutoModelForCausalLM.from_pretrained(
             model_name,
-            quantization_config=bnb_config,
-            cache_dir="./model_dir"
+            quantization_config=bnb_config
         ).to(device)
-        tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True, cache_dir="./model_dir")
+        tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
         if tokenizer.pad_token_id is None:
             tokenizer.pad_token_id = tokenizer.eos_token_id
         return model, tokenizer