Update app.py

app.py

@@ -3,9 +3,13 @@ from transformers import GPT2Tokenizer, GPT2LMHeadModel, AutoModelForSeq2SeqLM,
 import torch
 from langchain.memory import ConversationBufferMemory
 
+# Move model to device (GPU if available)
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+
 # Load the tokenizer and model for DistilGPT-2
 tokenizer = GPT2Tokenizer.from_pretrained("distilgpt2")
 model = GPT2LMHeadModel.from_pretrained("distilgpt2")
+model.to(device)
 
 # Load summarization model (e.g., T5-small)
 summarizer_tokenizer = AutoTokenizer.from_pretrained("t5-small")
@@ -20,10 +24,6 @@ def summarize_history(history):
     summary = summarizer_tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     return summary
 
-# Move model to device (GPU if available)
-device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
-model.to(device)
-
 # Set up conversational memory using LangChain's ConversationBufferMemory
 memory = ConversationBufferMemory()