End-of-RL checkpoint, full training state.

  • base: OLMo-2-1B, pretraining rung stage1-step110000-tokens231B
  • step 5000, fp32 weights + optimizer + scheduler + RNG + dataloader state
  • resumable, not an inference export
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support