Octo-Base
University of California (UC) BerkeleyStanford UniversityCarnegie Mellon University (CMU)DeepMindRobotic manipulationOpen weights
Developed by University of California (UC) Berkeley,Stanford University,Carnegie Mellon University (CMU),DeepMind in 2024, Octo-Base is a robotic manipulation model with 93000000.0 parameters with openly available weights.
About Octo-Base
Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-domain data, yet generalize bro
Details
- Provider
- University of California (UC) Berkeley,Stanford University,Carnegie Mellon University (CMU),DeepMind
- Task
- Robotic manipulation
- Parameters
- 93000000.0
- Released
- 2024-05-20
- Open weights
- Yes