IndexError: index out of range in self

🤗Transformers
1

I’m trying to a doc/qa answer via word_boxes params. But i’m getting this error when i pass in boundry boxes.

File "C:\repo\XOR\py\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\repo\XOR\py\lib\site-packages\torch\nn\modules\sparse.py", line 162, in forward
    return F.embedding(
  File "C:\repo\XOR\py\lib\site-packages\torch\nn\functional.py", line 2210, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self

my boxes look like this

[ ['than', (808, 1175, 12, 31)], ['_amount', (29, 1193, 22, 59)], ['(A)', (87, 1192, 23, 28)], ['above,', (120, 1192, 14, 47)], ['you', (173, 1195, 12, 25)], ['may', (204, 1195, 12, 30)], ['have', (239, 1192, 23, 35)], ['to', (278, 1193, 22, 14)], ['pay', (297, 1195, 20, 33)], ['a', (329, 1195, 9, 8)], ['tax', (341, 1193, 11, 21)], ['on', (368, 1195, 9, 17)], ['the', (390, 1192, 12, 23)], ['excess', (418, 1195, 9, 50)], ['contributions.', (473, 1192, 24, 106)], ['—', (576, 1183, 37, 8)]]


tokenizer = AutoTokenizer.from_pretrained("C:/repo/XOR/fasttext/docask/impira/layoutlm-document-qa")
model = AutoModelForDocumentQuestionAnswering.from_pretrained("C:/repo/XOR/fasttext/docask/impira/layoutlm-document-qa")


   ans = nlp(
                    fileName,
                    question=ques,
                    word_boxes=boxes
                )

Is the boxes correct? It does mention something about normalizing to 1-1000. Not sure what that means. Can someone let me know?