AI labsUnited States
OpenLM Research models
OpenLM Research is the project team behind OpenLLaMA, created by Xinyang Geng and Hao Liu of Berkeley AI Research. OpenLLaMA is a permissively licensed reproduction of Meta's LLaMA architecture trained on open data, including RedPajama and, for later releases, Falcon RefinedWeb and other sources.
- Scored models
- 1
- Best ranked
- OpenLLaMA 7B #864 of 896
- Newest
- OpenLLaMA 7B Jun 7, 2023
- Open weights
- 1 of 1
OpenLM Research models ranked by capability
Capability is Atlas's single score for each model, fitted to every sourced benchmark result (methodology). Rank is among all 896 ranked models from every lab.
| Model | Released | Capability | Rank | Benchmarks | Weights |
|---|---|---|---|---|---|
| OpenLLaMA 7B | Jun 7, 2023 | 73.7 | #864 | 6 | Open |