shaochenze/PatchTrain
Code for paper "Patch-Level Training for Large Language Models"
PythonApache-2.0
Issues
- 2
关于第二阶段的Token级别训练细节的问题
#2 opened by jyweky - 4
关于交叉熵的具体计算细节
#1 opened by JizhanFang
Code for paper "Patch-Level Training for Large Language Models"
PythonApache-2.0