Completed
56:50 Live evals on RWKV-7 and fine-tuning tips
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
How RWKV-7 "Goose" and Its Linear Inference Work
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Why is RWKV-7 Goose interesting
- 2 2:53 How to quickly run RWKV-7 Goose
- 3 4:04 What is RWKV-7
- 4 10:20 RNN’s forget things
- 5 12:33 First paper: Reinventing RNNs for the Transformer Era
- 6 24:22 Paper author Eugene Cheah joins the dive
- 7 36:43 The intuition behind each model layer
- 8 47:57 Parallelization during training
- 9 53:01 How well did RWKV-7 do on benchmarks?
- 10 56:50 Live evals on RWKV-7 and fine-tuning tips
- 11 1:00:38 Why they made the World Tokenizer
