423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix mod stuff

Browse Source
This commit is contained in:
hiyouga
2024-04-21 18:11:10 +08:00
parent d0273787be
commit f58425ab45
16 changed files with 63 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llmtuner/hparams/model_args.py
View File

@@ -63,15 +63,15 @@ class ModelArguments:
)
flash_attn: bool = field(
default=False,
metadata={"help": "Enable FlashAttention-2 for faster training."},
metadata={"help": "Enable FlashAttention for faster training."},
)
shift_attn: bool = field(
default=False,
metadata={"help": "Enable shift short attention (S^2-Attn) proposed by LongLoRA."},
)
mixture_of_depths: Optional[Literal["convert", "continue"]] = field(
mixture_of_depths: Optional[Literal["convert", "load"]] = field(
default=None,
metadata={"help": "Whether or not to use MoD in the model."},
metadata={"help": "Convert the model to mixture-of-depths (MoD) or load the MoD model."},
)
use_unsloth: bool = field(
default=False,