MT-NLG 530B (0-shot)

Reported on 1 benchmark 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.

Natural Language Processing1 result

Question AnsweringonPIQA
Accuracy· 2019-09-17
82
best: 90.1 (Unicorn 11B (fine-tuned))
SOTA
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism arXiv:1909.08053