Update app.py

app.py

@@ -6,14 +6,17 @@ import torch
 # Check if a GPU is available
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
+# Just for GPU 
 bnb_config = BitsAndBytesConfig(
         load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype="float16", bnb_4bit_use_double_quant=True
     )
 
 
 tokenizer = AutoTokenizer.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True, quantization_config=bnb_config)
+# 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)
 # Move the model to the GPU if available
 
 generation_config = GenerationConfig(
@@ -31,7 +34,7 @@ generation_config = GenerationConfig(
 # Define a function that takes a text input and generates a text output
 def generate_text(text):
     input_text = text
-    input_ids = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
     output_ids = model.generate(input_ids, generation_config=generation_config)
     output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
     return output_text