Update app.py

app.py

@@ -31,7 +31,8 @@ def bot(history):
     inputs=tokenizer(text,return_tensors='pt').to('cpu')
     with torch.no_grad():
       outputs=model.generate(**inputs,max_new_tokens=200,do_sample=True,top_p=0.92,top_k=10,temperature=0.7)
-    response=tokenizer.decode(outputs[0], skip_special_tokens=True)
+    output_text=outputs[:, inputs.input_ids.shape[1]:] 
+    response=tokenizer.decode(output_text[0], skip_special_tokens=True)
     print(response)
     history[-1][1] = ""
     for character in response[1:-1]: