p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update patcher.py

This commit is contained in:
hoshi-hiyouga 2024-01-22 23:27:39 +08:00 committed by GitHub
parent b06a31e76a
commit bdc9eff635
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/model/patcher.py
View File

@ -285,6 +285,7 @@ def patch_model(
_prepare_model_for_training(model, model_args) _prepare_model_for_training(model, model_args)
if getattr(model.config, "model_type", None) == "mixtral" and is_deepspeed_zero3_enabled(): if getattr(model.config, "model_type", None) == "mixtral" and is_deepspeed_zero3_enabled():
require_version("deepspeed>=0.13.0", "To fix: pip install deepspeed>=0.13.0")
from deepspeed.utils import set_z3_leaf_modules from deepspeed.utils import set_z3_leaf_modules
from transformers.models.mixtral.modeling_mixtral import MixtralSparseMoeBlock from transformers.models.mixtral.modeling_mixtral import MixtralSparseMoeBlock
set_z3_leaf_modules(model, [MixtralSparseMoeBlock]) set_z3_leaf_modules(model, [MixtralSparseMoeBlock])