zhiyuanhubj/LongRecipe
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Python
Issues
- 0
batch size设置大于1时会报shape不对等错误
#6 opened by 233function - 0
多机多卡设置
#5 opened by 233function - 1
seq_len设置
#4 opened by 233function - 1
replay_dataset
#3 opened by 233function - 2
- 3