分支列表

默认分支

92d63d4e8b · clean up fragile code · 最后更新于 2026-07-03 22:54:57 +00:00

分支列表

e4286f8b56 · compute multiplier comparisons between experiments · 最后更新于 2026-07-04 18:18:24 +00:00    frostbyte_neo

0
8

3a76bb9c00 · Add optional Mixture of Experts (MoE) addon, distilled from the moe2 branch · 最后更新于 2026-07-03 17:00:28 +00:00    frostbyte_neo

58
1
moe

5422d3a132 · make sure to use active params in scaling laws · 最后更新于 2026-02-19 02:46:36 +00:00    frostbyte_neo

103
4

69b1ed245e · also add base_train change example for how to swap LinearFP8 · 最后更新于 2026-01-13 17:08:10 +00:00    frostbyte_neo

219
2