Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models - Githubissues

wj-Mcat / wj-Mcat.github.io

小猫的技术杂货铺

https://wj-mcat.github.io/

5 stars 0 forks source link

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models #9

Open wj-Mcat opened 8 months ago

wj-Mcat commented 8 months ago

https://arxiv.org/abs/2401.01335