Update app.py

app.py

@@ -3,12 +3,12 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
 
 # Check if GPU is available, otherwise use CPU
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Load pre-trained GPT-2 model and tokenizer
 model_name = "gpt2-large"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def generate_text(input_text, max_length=16, num_beams=5, do_sample=False, no_repeat_ngram_size=2):
     """
@@ -25,7 +25,7 @@ def generate_text(input_text, max_length=16, num_beams=5, do_sample=False, no_re
     - generated_text (str): The generated text.
     """
     # Encode the input text and move it to the appropriate device
-    input_ids = tokenizer(input_text, return_tensors='pt')['input_ids'].to(device)
+    input_ids = tokenizer(input_text, return_tensors='pt')['input_ids']
     # Generate text using the model
     output = model.generate(input_ids, max_length=max_length, num_beams=num_beams,
                             do_sample=do_sample, no_repeat_ngram_size=no_repeat_ngram_size)
@@ -47,7 +47,7 @@ def generate_text_with_nucleus_search(input_text, max_length=128, do_sample=True
     - generated_text (str): The generated text.
     """
     # Encode the input text and move it to the appropriate device
-    input_ids = tokenizer(input_text, return_tensors='pt')['input_ids'].to(device)
+    input_ids = tokenizer(input_text, return_tensors='pt')['input_ids']
     # Generate text using nucleus sampling
     output = model.generate(input_ids, max_length=max_length, do_sample=do_sample, top_p=top_p)
     # Decode the generated output