Gerbil-B-3.3m

作者 GerbilLab · 下载 0 · 点赞 0 · 更新 2023-11-02

Model Name Parameters Class Ratio Tokens Batch Size (Tokens) Training Loss
GerbilLab/Gerbil-B-3.3m 3.3m B-Class 42 126M 65.5k 6.0822