TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Scaling Transformer to 1M tokens and beyond with RMT

Scaling Transformer to 1M tokens and beyond with RMT (arxiv.org)

232 points by panabee 3 years ago | 115 comments

Screenshot of arxiv.org: CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs

CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs (arxiv.org)

96 points by matt_d 5 months ago | 12 comments

Screenshot of arxiv.org: Scaling Transformers to 1B Tokens

Scaling Transformers to 1B Tokens (arxiv.org)

208 points by mottiden 3 years ago | 64 comments

Screenshot of arxiv.org: Inverted Transformers Are Effective for Time Series Forecasting

Inverted Transformers Are Effective for Time Series Forecasting (arxiv.org)

177 points by beefman 3 years ago | 27 comments

Screenshot of arxiv.org: Hierarchical Autoregressive Modeling for Memory-Efficient Language Generation

Hierarchical Autoregressive Modeling for Memory-Efficient Language Generation (arxiv.org)

40 points by PaulHoule 9 months ago | 1 comments

Screenshot of arxiv.org: A Mathematical Perspective on Transformers

A Mathematical Perspective on Transformers (arxiv.org)

63 points by georgehill 2 years ago | 4 comments