Actions: huggingface/trl
Actions
205 workflow run results
205 workflow run results
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1636:
Pull request #912
synchronize
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1635:
Pull request #912
synchronize
by
younesbelkada
SFTTrainer
] Make sure to not conflict between transformers
and TRL implementation
Build PR Documentation
#1631:
Pull request #933
synchronize
by
younesbelkada
SFTTrainer
] Make sure to not conflict between transformers
and TRL implementation
Build PR Documentation
#1630:
Pull request #933
synchronize
by
younesbelkada
SFTTrainer
] Make sure to not conflict between transformers
and TRL implementation
Build PR Documentation
#1629:
Pull request #933
opened
by
younesbelkada
tyro
version
Build PR Documentation
#1625:
Pull request #928
opened
by
brentyi
DPO
] fix DPO + GC issues
Build PR Documentation
#1621:
Pull request #927
opened
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1615:
Pull request #912
reopened
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1614:
Pull request #912
synchronize
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1613:
Pull request #912
synchronize
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1612:
Pull request #912
synchronize
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1611:
Pull request #912
synchronize
by
younesbelkada
core
/ DDP
] Fix RM trainer + DDP + quantization + propagate gradient_checkpointing_kwargs
in SFT & DPO
Build PR Documentation
#1610:
Pull request #912
synchronize
by
younesbelkada