Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs
Imported from official source
Olmo-core 3 introduces a redesigned, fully open training stack for efficiently scaling mixture-of-experts models into the trillion-parameter range.
This version
- Version
- 1 of 1
- Recorded
- October 01, 2026 16:00
- Change
- Initial
- Content hash
8b6b7e75f6efb374f08e3c4fe3c9dd95- All versions
- Revision history