∞-former (Sticky memories + initialized GPT-2 Small)
Reported on 5 benchmarks across 5 tasks · 1 paper · 4 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Speech1 result
Adversarial1 result
- Perplexity· uses extra data· 2021-09-01SOTA32.48
Methodology1 result
Natural Language Processing1 result
- Perplexity· uses extra data· 2021-09-01SOTA32.48
Medical1 result
- Test perplexity· uses extra data· 2021-09-0116.61best: 2.4 (RETRO (7.5B))