Annotated Implementation of DeepNet: Scaling Transformers to 1k Layers (nn.labml.ai)

3 points by vpj 4y ago ↗ HN

0 comments

[ 3.5 ms ] story [ 12.9 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats