ViperEkura 1169cfad82 fix(trainer): 修复多轮对话中的因果注意力掩码计算逻辑等

2025-09-28 15:15:19 +08:00

..

core

fix(trainer): 修复多轮对话中的因果注意力掩码计算逻辑等

2025-09-28 15:15:19 +08:00

trainer

fix(trainer): 修复多轮对话中的因果注意力掩码计算逻辑等

2025-09-28 15:15:19 +08:00

utils

Initial commit

2025-09-27 12:02:22 +08:00

__init__.py

Initial commit

2025-09-27 12:02:22 +08:00

model.py

Initial commit

2025-09-27 12:02:22 +08:00