YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

0.5B MoE in training, saving as public because I don't have enough private repo space sorry. DCP format.

Those are intermediate checkpoints, 1 iter = 1M tokens. So, 1600 iter checkpoint was trained on 1.6B tokens.

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