GitHub - JonasGeiping/cramming: Cramming the training of a (BERT-type) language model into limited compute. - discu.eu

Linking pages

GitHub - PiotrNawrot/nanoT5: Fast & Simple repository for pre-training and fine-tuning T5-style models https://github.com/PiotrNawrot/nanoT5 0 comments

Linked pages

pre-commit https://pre-commit.com 96 comments
[2212.14034] Cramming: Training a Language Model on a Single GPU in One Day https://arxiv.org/abs/2212.14034 25 comments
GitHub - HazyResearch/flash-attention: Fast and memory-efficient exact attention https://github.com/HazyResearch/flash-attention 3 comments

Related searches:

Search whole site: site:github.com

Search title: GitHub - JonasGeiping/cramming: Cramming the training of a (BERT-type) language model into limited compute.

See how to search.

Submit link to: