423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 04:32:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

add hint

Browse Source 
Former-commit-id: e4ba1deedfc366c984f0095b250ed42a57c3dfba
This commit is contained in:
hiyouga 2024-01-22 23:32:01 +08:00
parent 8196e9f806
commit 60a042cc16
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/model/patcher.py
View File

@ -286,7 +286,7 @@ def patch_model(
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") 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 # type: ignore
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])