Update app.py

app.py

@@ -3,6 +3,8 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig,B
 
 import torch
 
+model_id = "truongghieu/deci-finetuned_BK_Regulation"
+
 # Check if a GPU is available
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
@@ -12,10 +14,10 @@ bnb_config = BitsAndBytesConfig(
     )
 
 
-tokenizer = AutoTokenizer.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 # Load model in this way if use GPU
-model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True, quantization_config=bnb_config)
-# model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True)
+# model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, quantization_config=bnb_config)
+model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True)
 # Move the model to the GPU if available
 
 generation_config = GenerationConfig(