423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 18:20:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] add qwen3-vl/qwen3-omni (#9196)

Browse Source 
Co-authored-by: kingsley <kingsleydodonow@gmail.com>
This commit is contained in:
xvxuopop
2025-09-27 01:21:47 +08:00
committed by GitHub
parent abc3b1e1c4
commit 0761a4448f
5 changed files with 268 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -105,7 +105,7 @@ def add_z3_leaf_module(model: "PreTrainedModel") -> None:
_set_z3_leaf_modules(model, [Qwen2MoeSparseMoeBlock])
if model_type == "qwen3_moe" or text_architectures == "Qwen3MoeForCausalLM": # for internvl_3_5
if model_type == "qwen3_moe" or text_architectures == "Qwen3MoeForCausalLM":
from transformers.models.qwen3_moe.modeling_qwen3_moe import Qwen3MoeSparseMoeBlock
_set_z3_leaf_modules(model, [Qwen3MoeSparseMoeBlock])