Base model: open-thoughts/OpenThinker-7B
open-thoughts/OpenThinker-7B
SFT model: yufeng1/OpenThinker-7B-reasoning-full-lora-max-type3-e5-2
yufeng1/OpenThinker-7B-reasoning-full-lora-max-type3-e5-2
Merge method: slerp
slerp
Alpha: 0.25
0.25
Validation reasoning rate: 99.06666666666666
99.06666666666666
Chat template
Files info