423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-24 23:02:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update patcher.py

Browse Source 
Former-commit-id: bdc9eff635cbea670722e672fd329ac35a01a812
This commit is contained in:
hoshi-hiyouga 2024-01-22 23:27:39 +08:00 committed by GitHub
parent f00ad6b4f8
commit 68977c8ca4
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)
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 transformers.models.mixtral.modeling_mixtral import MixtralSparseMoeBlock
set_z3_leaf_modules(model, [MixtralSparseMoeBlock])