b0e4fff 790f2f1
1
2
3
4
5
6
7
8
9
10
--- datasets: - open-web-math/open-web-math --- Mistral-7b with continued pretraining using Quiet-STaR (https://arxiv.org/abs/2403.09629) for generating 8 thought tokens before each output token. Forked from Crystalcareai/Quiet-Star-Custom
