YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
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.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support