423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 11:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[misc] fix omni thinker load (#9552)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Kingsley
2025-11-30 09:36:36 +08:00
committed by GitHub
parent d1f585f80a
commit 22be45c78c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/model/model_utils/moe.py
View File

@@ -127,7 +127,7 @@ def add_z3_leaf_module(model: "PreTrainedModel") -> None:
_set_z3_leaf_modules(model, [Qwen3VLMoeTextSparseMoeBlock]) _set_z3_leaf_modules(model, [Qwen3VLMoeTextSparseMoeBlock])
if model_type == "qwen3_omni_moe": if model_type in ("qwen3_omni_moe", "qwen3_omni_moe_thinker"):
from transformers.models.qwen3_omni_moe.modeling_qwen3_omni_moe import Qwen3OmniMoeThinkerTextSparseMoeBlock from transformers.models.qwen3_omni_moe.modeling_qwen3_omni_moe import Qwen3OmniMoeThinkerTextSparseMoeBlock
_set_z3_leaf_modules(model, [Qwen3OmniMoeThinkerTextSparseMoeBlock]) _set_z3_leaf_modules(model, [Qwen3OmniMoeThinkerTextSparseMoeBlock])