Compressive Transformer (18L, M=1024)
Reported on 2 benchmarks across 1 task · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Medical2 results
- Test perplexity· 2019-11-1317.1best: 2.4 (RETRO (7.5B))
- Validation perplexity· 2019-11-1316best: 13.11 (Ensemble of All)