HackerTrans
トップ新着トレンドコメント過去質問紹介求人

ZQ-Dev8

no profile record

投稿

Unsloth creators fix universal error with gradient accumulation

unsloth.ai
4 ポイント·投稿者 ZQ-Dev8·2 年前·2 コメント

コメント

ZQ-Dev8
·昨年·議論
How's this compare with docling (https://github.com/docling-project/docling)?
ZQ-Dev8
·2 年前·議論
Jeremy, this is awesome! Personally excited for a new wave of sentence transformers built off ModernBERT. A poster below provided the link to a sample ST training script in the ModernBERT repo, so that's great.

Do you expect the ModernBERT STs to carry the same advantages over ModernBERT that BERT STs had over the original BERT? Or would you expect caveats based on ModernBERT's updated architecture and capabilities?
ZQ-Dev8
·2 年前·議論
seems like something pytorch maintainers would want to know about and fix asap...