Update app.py

app.py

@@ -15,37 +15,33 @@ chat_history_ids = None
 
 def chat(user_input, history):
     global chat_history_ids
-    
-    # Encode input
-# Add personality + context prompt
-prompt = "You are a helpful, friendly, and intelligent assistant. Give clear, meaningful, and human-like responses.\nUser: " + user_input + "\nBot:"
-
-new_input_ids = tokenizer.encode(prompt + tokenizer.eos_token, return_tensors='pt')
-    
-    # Append to chat history
+
+    # Add personality prompt
+    prompt = "You are a helpful, friendly, and intelligent assistant. Give clear, meaningful, and human-like responses.\nUser: " + user_input + "\nBot:"
+
+    new_input_ids = tokenizer.encode(prompt + tokenizer.eos_token, return_tensors='pt').to(device)
+
     if chat_history_ids is not None:
         input_ids = torch.cat([chat_history_ids, new_input_ids], dim=-1)
     else:
         input_ids = new_input_ids
-    
-    # Generate response
-chat_history_ids = model.generate(
-    input_ids,
-    max_length=1000,
-    pad_token_id=tokenizer.eos_token_id,
-    do_sample=True,
-    top_k=50,
-    top_p=0.95,
-    temperature=0.8,
-    repetition_penalty=1.2
-)
-    
-    # Decode response
+
+    chat_history_ids = model.generate(
+        input_ids,
+        max_length=1000,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        top_k=50,
+        top_p=0.95,
+        temperature=0.8,
+        repetition_penalty=1.2
+    )
+
     response = tokenizer.decode(
         chat_history_ids[:, input_ids.shape[-1]:][0],
         skip_special_tokens=True
     )
-    
+
     return response
 
 # Gradio UI