We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of the blocks to improve upon the current Transformer architecture and proposed PAR Transformer. It needs 35% lower compute time than Transformer-XL achieved by replacing ~63% of the self-attention blocks with feed-forward blocks, and retains the perplexity on WikiText-103 language modelling benchmark. We further validated our results on text8 and enwiki8 datasets, as well as on the BERT model.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2009.04534")
get_code_for_paper("2009.04534")
have("2009.04534")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2009.04534.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2009.04534)
Connect an agent — have() is free.