ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix mod stuff

Browse Source 
Former-commit-id: cf3988226e6398c67bb2955578e436fc505aa5c5
This commit is contained in:
hiyouga
2024-04-21 18:11:10 +08:00
parent 3365cc8cf0
commit f8e219dc81
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,

4
src/llmtuner/hparams/parser.py
View File

@@ -82,8 +82,8 @@ def _check_extra_dependencies(
if model_args.use_unsloth:
require_version("unsloth", "Please install unsloth: https://github.com/unslothai/unsloth")
if model_args.mixture_of_depths == 'convert' or model_args.mixture_of_depths == 'continue':
require_version("mixture-of-depth", "To fix: pip install mixture-of-depth")
if model_args.mixture_of_depths is not None:
require_version("mixture-of-depth>=1.1.6", "To fix: pip install mixture-of-depth>=1.1.6")
if model_args.infer_backend == "vllm":
require_version("vllm>=0.3.3", "To fix: pip install vllm>=0.3.3")