PAR Transformer 24B

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Language Modellingonenwiki8
Bit per Character (BPC)· 2020-09-09
1.11
SOTA
Pay Attention when Required arXiv:2009.04534
Language ModellingonText8
Bit per Character (BPC)· 2020-09-09
1.18
best: 1.63 (td-LSTM (Zhang et al., 2016))
Pay Attention when Required arXiv:2009.04534