🅰️🅾️ 👋

🎓 PhD Student @SapienzaNLP

Sapienza University of Rome

Contacts

Cool Projects

🎓 Minerva LLMs

🦮 Golden Retriever

Stats

golden-retriever's People

Stargazers

Watchers

golden-retriever's Issues

deberta-base models do not work.

The retriever do not work if using deberta as the encoder model.

Code:

    retriever = GoldenRetriever(
        question_encoder="microsoft/deberta-v3-base",
        document_index=InMemoryDocumentIndex(
                documents=DocumentStore.from_file(
                    "index/path"
                ),
                metadata_fields=[],
                separator=' <def> ',
                device="cuda"
            ),
            devide="cuda"

    )
    retriever.index()

Error:


UserWarning: The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option which is not implemented in the fast tokenizers. In practice this means that the fast version of the tokenizer can produce unknown tokens whereas the sentencepiece version would have converted these unknown tokens into a sequence of byte tokens matching the original piece of text.
 
 Traceback (most recent call last):
  File "retriever.py", line 159, in <module>
    train()
  File "retriever.py", line 148, in train
    retriever.index()
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "envs/retriever/lib/python3.10/site-packages/goldenretriever/pytorch_modules/model.py", line 239, in index
    return self.document_index.index(
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "envs/retriever/lib/python3.10/site-packages/goldenretriever/indexers/inmemory.py", line 222, in index
    for batch in tqdm(dataloader, desc="Indexing"):
  File "envs/retriever/lib/python3.10/site-packages/tqdm/std.py", line 1181, in __iter__
    for obj in iterable:
  File "/home/alessandroscire/miniconda3/envs/retriever/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 631, in __next__
    data = self._next_data()
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1346, in _next_data
    return self._process_data(data)
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1372, in _process_data
    data.reraise()
  File "envs/retriever/lib/python3.10/site-packages/torch/_utils.py", line 722, in reraise
    raise exception
OverflowError: Caught OverflowError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
    data = fetcher.fetch(index)
  File "envs/retriever/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
    return self.collate_fn(data)
  File "envs/retriever/lib/python3.10/site-packages/goldenretriever/indexers/inmemory.py", line 181, in collate_fn
    tokenizer(
  File "envs/retriever/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2803, in __call__
    encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs)
  File "envs/retriever/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2889, in _call_one
    return self.batch_encode_plus(
  File "envs/retriever/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3080, in batch_encode_plus
    return self._batch_encode_plus(
  File "envs/retriever/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 496, in _batch_encode_plus
    self.set_truncation_and_padding(
  File "envs/retriever/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 451, in set_truncation_and_padding
    self._tokenizer.enable_truncation(**target)
OverflowError: int too big to convert

Recommend Projects