Introduction
Get Started
Prepare your data
Cerebras PyTorch API
cerebras_pytorch
cerebras_pytorch.amp
cerebras_pytorch.optim
cerebras_pytorch.sparse
cerebras_pytorch.metrics
Cerebras Model Zoo
Cerebras Guides
Fundamentals
Support
Download files needed for tokenization for dataset creation.
args (argparse namespace) – Arguments for downloading the tokenizer files.
previous
modelzoo.transformers.data_processing.scripts.pile.download.download_pile
next
modelzoo.transformers.data_processing.scripts.pile.download.get_urls_for_tokenizer_files