Hybrid H3 125M

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 ModellingonThe Pile
Test perplexity· 2022-12-28
10.2
best: 10 (Larger Transformer 771M (fine-tuned))
SOTA
Hungry Hungry Hippos: Towards Language Modeling with State Space Models arXiv:2212.14052
Language ModellingonWikiText-103
Test perplexity· 2022-12-28
18.5
best: 2.4 (RETRO (7.5B))
Hungry Hungry Hippos: Towards Language Modeling with State Space Models arXiv:2212.14052