.

app.py

@@ -14,13 +14,16 @@ MAX_RESULT_TOKENS = 10
 @spaces.GPU
 def predict_answer(question):
     input_text = ' '.join(question.split()).strip() + ' ' + tokenizer.eos_token
+    print (input_text)
     inputs = tokenizer(input_text, return_tensors='pt').to('cuda' if torch.cuda.is_available() else 'cpu')
     implicit_cot_model.to('cuda' if torch.cuda.is_available() else 'cpu')
 
     input_ids = inputs['input_ids']
+    print (input_ids)
     outputs = implicit_cot_model.generate(input_ids=input_ids,
             max_new_tokens=MAX_RESULT_TOKENS,
             do_sample=False)
+    print (outputs)
 
     prediction = tokenizer.decode(outputs[0], skip_special_tokens=True)