model:
32B olmo-2 03/25
https://arxiv.org/abs/2501.00656
"We release all OLMo 2 artifacts openly – models at 7B and 13B scales, both pretrained and post-trained, including their full training data, training code and recipes, training logs and thousands of intermediate checkpoints. "
Nice. You should probably mention what makes this model special. That this is an open model, with the dataset and everything available.