OPT 2.7B

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.

Medical1 result

Language ModellingonThe Pile
Test perplexity· 2022-10-04
17.81
best: 10 (Larger Transformer 771M (fine-tuned))
SOTA
Knowledge Unlearning for Mitigating Privacy Risks in Language Models arXiv:2210.01504