open_llama_7b
#264 of 274 scored.
MetaJun 7, 2023
Capabilities Index
Range 76.9–99.2
91.7
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run open_llama_7b yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- HellaSwag62.4%
- PIQA52.0%
- Winogrande34.0%
- OpenBookQA18.7%
- ARC AI218.3%
- MMLU6.5%
On the index
Around it.
Sources