Premium Only Content

RWKV: Reinventing RNNs for the Transformer Era (Paper Explained)
#gpt4 #rwkv #transformer
We take a look at RWKV, a highly scalable architecture between Transformers and RNNs.
Fully Connected (June 7th in SF) Promo Link: https://www.fullyconnected.com/?promo=ynnc
OUTLINE:
0:00 - Introduction
1:50 - Fully Connected In-Person Conference in SF June 7th
3:00 - Transformers vs RNNs
8:00 - RWKV: Best of both worlds
12:30 - LSTMs
17:15 - Evolution of RWKV's Linear Attention
30:40 - RWKV's Layer Structure
49:15 - Time-Parallel vs Sequence Mode
53:55 - Experimental Results & Limitations
58:00 - Visualizations
1:01:40 - Conclusion
Paper: https://arxiv.org/abs/2305.13048
Code: https://github.com/BlinkDL/RWKV-LM
Abstract:
Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in memory and computational requirements but struggle to match the same performance as Transformers due to limitations in parallelization and scalability. We propose a novel model architecture, Receptance Weighted Key Value (RWKV), that combines the efficient parallelizable training of Transformers with the efficient inference of RNNs. Our approach leverages a linear attention mechanism and allows us to formulate the model as either a Transformer or an RNN, which parallelizes computations during training and maintains constant computational and memory complexity during inference, leading to the first non-transformer architecture to be scaled to tens of billions of parameters. Our experiments reveal that RWKV performs on par with similarly sized Transformers, suggesting that future work can leverage this architecture to create more efficient models. This work presents a significant step towards reconciling the trade-offs between computational efficiency and model performance in sequence processing tasks.
Authors: Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Huanqi Cao, Xin Cheng, Michael Chung, Matteo Grella, Kranthi Kiran GV, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartlomiej Koptyra, Hayden Lau, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Xiangru Tang, Bolun Wang, Johan S. Wind, Stansilaw Wozniak, Ruichong Zhang, Zhenyuan Zhang, Qihang Zhao, Peng Zhou, Jian Zhu, Rui-Jie Zhu
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
-
LIVE
Dear America
51 minutes agoLUNATICS Protest DC Crime Being Down 30%?! + FBI Catches A TOP MOST WANTED!!
9,007 watching -
LIVE
LFA TV
2 hours agoLFA TV ALL DAY STREAM - THURSDAY 8/21/25
10,761 watching -
LIVE
The Bubba Army
22 hours agoAnother LopSided Jake Paul Fight? - Bubba the Love Sponge® Show | 8/21/25
6,249 watching -
1:02:42
Dialogue works
1 day ago $3.19 earnedJohn Helmer: Trump Ditches Ceasefire? Despite EU & Zelensky Pressure
46.9K19 -
10:48
Nikko Ortiz
20 hours agoDont Watch These TikToks
84K13 -
10:17
MattMorseTV
19 hours ago $15.30 earnedTrump's DOJ just DROPPED a NUKE.
87.2K94 -
2:09:32
Side Scrollers Podcast
22 hours agoStreamer DIES Live On Air + Your Food is Poison + Xbox Announces $900 Handheld | Side Scrollers Live
41.1K13 -
15:32
GritsGG
17 hours agoFull Auto ABR Sniper Support! Most Winning Quad Win Streaking!
24.7K4 -
7:42
The Pascal Show
17 hours ago $1.98 earnedBREAKING! Police Provide UPDATE In Emmanuel Haro's Case! Is Jake's Lawyer Lying To Us?!
32.7K2 -
2:29:46
FreshandFit
10 hours agoAfter Hours w/ Girls
135K92