423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 10:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] efficient tuning for gpt-oss (#9354)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
thulyubh22
2025-12-23 16:28:38 +08:00
committed by GitHub
parent 1f1f5a7d1b
commit 7901b2f32e
3 changed files with 18 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llamafactory/model/model_utils/liger_kernel.py
View File

@@ -77,6 +77,9 @@ def apply_liger_kernel(
from liger_kernel.transformers import apply_liger_kernel_to_qwen3 as apply_liger_kernel
elif model_type == "qwen3_moe":
from liger_kernel.transformers import apply_liger_kernel_to_qwen3_moe as apply_liger_kernel
elif model_type == "gpt_oss":
# Install manually from https://github.com/Comet0322/Liger-Kernel
from liger_kernel.transformers import apply_liger_kernel_to_gpt_oss as apply_liger_kernel
else:
logger.warning_rank0("Current model does not support liger kernel.")
return