一张卡train不起来

Ucas-HaoranWei / Vary-toy

Official code implementation of Vary-toy (Small Language Model Meets with Reinforced Vision Vocabulary)

565 stars 41 forks source link

Open fanshuaiyao opened 2 weeks ago

fanshuaiyao commented 2 weeks ago

请问最低配置是多少，我在一张RTX4090上训练，batch_size一直降低到了1，model_max_length = 1024还是没跑起来，显存爆了