YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
numbat nano-200M
A complete numbat-nano, 14T parameters shrinked down to 200 Million parameters with the same architecture. It uses BF16. Note that this uses completely random weights, and i didn't train it either. Warning: some of the files are data about the actual numbat(like the evaluations, etc.)
- Downloads last month
- 123
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support