Dolly 2.0-12b
#268 of 274 scored.
DatabricksApr 11, 2023Open weights
Capabilities Index
Range 73.6–97.5
89.7
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run Dolly 2.0-12b yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- HellaSwag61.1%
- PIQA50.8%
- Winogrande23.6%
- ARC AI219.5%
- OpenBookQA18.9%
- MMLU1.6%
On the index
Around it.
Sources