Completed
- RWKV's Layer Structure
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
RWKV- Reinventing RNNs for the Transformer Era
Automatically move to the next video in the Classroom when playback concludes
- 1 - Introduction
- 2 - Fully Connected In-Person Conference in SF June 7th
- 3 - Transformers vs RNNs
- 4 - RWKV: Best of both worlds
- 5 - LSTMs
- 6 - Evolution of RWKV's Linear Attention
- 7 - RWKV's Layer Structure
- 8 - Time-Parallel vs Sequence Mode
- 9 - Experimental Results & Limitations
- 10 - Visualizations
- 11 - Conclusion
