Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)

https://is1-ssl.mzstatic.com/image/thumb/Podcasts125/v4/ff/33/99/ff339999-e715-de98-bfa9-434d2ec02741/mza_7651343110096145581.jpg/600x600bb.jpg

Yannic Kilcher Videos (Audio Only)

Yannic Kilcher

177 episodes

3 days ago

I make videos about machine learning research papers, programming, and issues of the AI community, and the broader impact of AI in society. Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar (preferred to Patreon): https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq

Technology

RSS

All content for Yannic Kilcher Videos (Audio Only) is the property of Yannic Kilcher and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Technology

https://d3t3ozftmdmh3i.cloudfront.net/production/podcast_uploaded_nologo/14910857/14910857-1619956737934-aa3bd63307833.jpg

Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)

Yannic Kilcher Videos (Audio Only)

24 minutes 33 seconds

2 years ago

Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)

#ai #transformer #gpt4 This paper promises to scale transformers to 1 million tokens and beyond. We take a look at the technique behind it: The Recurrent Memory Transformer, and what its strenghts and weaknesses are. OUTLINE: 0:00 - Intro 2:15 - Transformers on long sequences 4:30 - Tasks considered 8:00 - Recurrent Memory Transformer 19:40 - Experiments on scaling and attention maps 24:00 - Conclusion Paper: https://arxiv.org/abs/2304.11062 Abstract: This technical report presents the application of a recurrent memory to extend the context length of BERT, one of the most effective Transformer-based models in natural language processing. By leveraging the Recurrent Memory Transformer architecture, we have successfully increased the model's effective context length to an unprecedented two million tokens, while maintaining high memory retrieval accuracy. Our method allows for the storage and processing of both local and global information and enables information flow between segments of the input sequence through the use of recurrence. Our experiments demonstrate the effectiveness of our approach, which holds significant potential to enhance long-term dependency handling in natural language understanding and generation tasks as well as enable large-scale context processing for memory-intensive applications. Authors: Aydar Bulatov, Yuri Kuratov, Mikhail S. Burtsev Links: Homepage: https://ykilcher.com Merch: https://ykilcher.com/merch YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ykilcher.com/discord LinkedIn: https://www.linkedin.com/in/ykilcher If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://www.subscribestar.com/yannickilcher Patreon: https://www.patreon.com/yannickilcher Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n