peak-reasoning
Collection
⚠️DEPRECATED: Please switch to the Steiner-preview series models, which are trained with reinforcement learning and backtrack-able synthetic datasets. • 3 items • Updated • 1
⚠️DEPRECATED: Please switch to the Steiner-preview series models, which are trained with reinforcement learning and backtrack-able synthetic datasets.
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Base model
peakji/peak-reasoning-7b