Releasesby Glyphopen-instruct 0.2.0
Notable changelog items: 1. Fixed a major but where ZeRO-2 was discarding gradients. 2. We now support training with a RLEnvironment abstraction, including code execution sandboxing. 3. The Olmo-core DPO is ready to go, with support for TP, packing, and torch.compile. This should be much faster than the previous HF implementation. 4.