Mamba-2.8B

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Medical2 results

Language ModellingonLAMBADA
Accuracy· 2023-12-01
69.2
best: 89.7 (PaLM-540B (Few-Shot))
Mamba: Linear-Time Sequence Modeling with Selective State Spaces arXiv:2312.00752
Language ModellingonLAMBADA
Perplexity· 2023-12-01
4.23
best: 1.92 (GPT-3 175B (Few-Shot))
Mamba: Linear-Time Sequence Modeling with Selective State Spaces arXiv:2312.00752

Natural Language Processing1 result

Sentence CompletiononHellaSwag
Accuracy· 2023-12-01
66.1
best: 96.1 (CompassMTL 567M with Tailor)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces arXiv:2312.00752