Update app.py

app.py

@@ -13,8 +13,19 @@ model.config.pad_token_id = model.config.eos_token_id
 @spaces.GPU
 def chat(prompt):
     input_ids = tokenizer.encode(prompt, return_tensors="pt")
-    output = model.generate(input_ids, max_length=1024, num_return_sequences=1, top_p=0.9, top_k=1)
-    response = tokenizer.decode(output[0])
+    attention_mask = torch.ones_like(input_ids)
+    
+    output = model.generate(
+        input_ids,
+        attention_mask=attention_mask,
+        max_length=1024,
+        num_return_sequences=1,
+        top_p=0.9,
+        top_k=1,
+        pad_token_id=model.config.eos_token_id
+    )
+    
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
     return response
 
 demo = gr.Interface(