Extremely Small BERT Models from Mixed-Vocabulary Training — mentioned by dmezzetti

Tue, 26 Dec 2023 02:07:18 GMT

For those interested in micro/tiny/small models, a couple more links. https://arxiv.org/abs/1909.11687 https://arxiv.org/abs/2210.07904 I wrote an article on the subject earlier this year - https://neuml.hashnode.dev/train-a-language-model-from-scrat...

Paper and discussion history. A mention is not an endorsement.

Extremely Small BERT Models from Mixed-Vocabulary Training — HN submission

Sun, 29 Sep 2019 02:30:17 GMT

Extreme Language Model Compression with Optimal Subwords and Shared Projections

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Extremely Small BERT Models from Mixed-Vocabulary Training · HackerPapers discussions

Extremely Small BERT Models from Mixed-Vocabulary Training — mentioned by dmezzetti

Extremely Small BERT Models from Mixed-Vocabulary Training — HN submission