はてなブックマーク - GitHub - kyegomez/BitNet: Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch https://b.hatena.ne.jp/entry/s/github.com/kyegomez/BitNet PyTorch Implementation of the linear methods and model from the paper "BitNet: Scaling 1-bit Transformers for Large Language Models" Paper link: BitLinear = tensor -> layernorm -> Binarize -> abs m... ussiik1 https://b.hatena.ne.jp/ussiik1/20240309#bookmark-4749932097800407360 2024-03-09T00:04:44Z barlog https://b.hatena.ne.jp/barlog/20240305#bookmark-4749932097800407360 2024-03-05T00:47:45Z stealthinu https://b.hatena.ne.jp/stealthinu/20240302#bookmark-4749932097800407360 BitNetのアンオフィシャル実装。ちゃんときれいに学習進むらしい。めちゃすごい勢いで実装が進んでいくな。 2024-03-02T10:28:46Z deeplearning LLM misshiki https://b.hatena.ne.jp/misshiki/20240229#bookmark-4749932097800407360 “BitNet”公式リポジトリ。 2024-02-29T04:58:42Z 自然言語処理 Transformer PyTorch ZAORIKU https://b.hatena.ne.jp/ZAORIKU/20240229#bookmark-4749932097800407360 2024-02-29T03:18:03Z jack0909 https://b.hatena.ne.jp/jack0909/20240229#bookmark-4749932097800407360 2024-02-28T23:17:24Z iqm https://b.hatena.ne.jp/iqm/20240228#bookmark-4749932097800407360 2024-02-28T12:26:26Z yuiseki https://b.hatena.ne.jp/yuiseki/20240228#bookmark-4749932097800407360 2024-02-28T11:35:01Z あとで読む unfini https://b.hatena.ne.jp/unfini/20240228#bookmark-4749932097800407360 2024-02-28T11:25:03Z github LLM 言語 takutakuma https://b.hatena.ne.jp/takutakuma/20240228#bookmark-4749932097800407360 2024-02-28T11:07:06Z kybernetes https://b.hatena.ne.jp/kybernetes/20240228#bookmark-4749932097800407360 2024-02-28T11:05:18Z LLM R2M https://b.hatena.ne.jp/R2M/20240228#bookmark-4749932097800407360 2024-02-28T10:39:44Z LLM mickn https://b.hatena.ne.jp/mickn/20240228#bookmark-4749932097800407360 1-bit LLM 2024-02-28T10:14:42Z razokulover https://b.hatena.ne.jp/razokulover/20240228#bookmark-4749932097800407360 2024-02-28T08:43:09Z