Skip to content

feat(transformers): add hunyuan v1 dense/moe (v4.57.1) #1401

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

feat(transformers): add hunyuan v1 dense/moe (v4.57.1) #1401

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
81e7415
add hunyuanv1 modeling scripts
Fzilan Oct 28, 2025
3cd1d85
add fast ut
Fzilan Oct 29, 2025
e87277c
bugfix
Fzilan Oct 29, 2025
4f0a847
fix typo
Fzilan Oct 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions mindone/transformers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1575,6 +1575,8 @@
from .models.vjepa2 import VJEPA2ForVideoClassification, VJEPA2Model, VJEPA2PreTrainedModel

if version.parse(transformers.__version__) >= version.parse("4.57.0"):
from .models.hunyuan_v1_dense import HunYuanDenseV1ForCausalLM, HunYuanDenseV1ForSequenceClassification
from .models.hunyuan_v1_moe import HunYuanMoEV1ForCausalLM, HunYuanMoEV1ForSequenceClassification
from .models.qwen3_vl import (
Qwen3VLForConditionalGeneration,
Qwen3VLModel,
Expand Down
2 changes: 1 addition & 1 deletion mindone/transformers/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -275,4 +275,4 @@
from . import glm4v, minimax, qwen2_5_omni, vjepa2

if version.parse(transformers.__version__) >= version.parse("4.57.0"):
from . import qwen3_vl, qwen3_vl_moe
from . import hunyuan_v1_dense, hunyuan_v1_moe, qwen3_vl, qwen3_vl_moe
4 changes: 4 additions & 0 deletions mindone/transformers/models/auto/configuration_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,6 +126,8 @@
("helium", "HeliumConfig"),
("hiera", "HieraConfig"),
("hubert", "HubertConfig"),
("hunyuan_v1_dense", "HunYuanDenseV1Config"),
("hunyuan_v1_moe", "HunYuanMoEV1Config"),
("ibert", "IBertConfig"),
("idefics", "IdeficsConfig"),
("idefics2", "Idefics2Config"),
Expand Down Expand Up @@ -394,6 +396,8 @@
("helium", "Helium"),
("hiera", "Hiera"),
("hubert", "Hubert"),
("hunyuan_v1_dense", "HunYuanDenseV1"),
("hunyuan_v1_moe", "HunYuanMoEV1"),
("ibert", "I-BERT"),
("idefics", "IDEFICS"),
("idefics2", "Idefics2"),
Expand Down
7 changes: 7 additions & 0 deletions mindone/transformers/models/auto/modeling_auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,6 +120,8 @@
("helium", "HeliumModel"),
("hiera", "HieraModel"),
("hubert", "HubertModel"),
("hunyuan_v1_dense", "HunYuanDenseV1Model"),
("hunyuan_v1_moe", "HunYuanMoEV1Model"),
("ibert", "IBertModel"),
("idefics", "IdeficsModel"),
("idefics2", "Idefics2Model"),
Expand Down Expand Up @@ -449,6 +451,9 @@
("granite", "GraniteForCausalLM"),
("granitemoe", "GraniteMoeForCausalLM"),
("granitemoeshared", "GraniteMoeSharedForCausalLM"),
("helium", "HeliumForCausalLM"),
("hunyuan_v1_dense", "HunYuanDenseV1ForCausalLM"),
("hunyuan_v1_moe", "HunYuanMoEV1ForCausalLM"),
("jetmoe", "JetMoeForCausalLM"),
("layoutlm", "LayoutLMForMaskedLM"),
("jamba", "JambaForCausalLM"),
Expand Down Expand Up @@ -879,6 +884,8 @@
("gpt_neox", "SequenceClassification"),
("helium", "HeliumForSequenceClassification"),
("hubert", "HubertForSequenceClassification"),
("hunyuan_v1_dense", "HunYuanDenseV1ForSequenceClassification"),
("hunyuan_v1_moe", "HunYuanMoEV1ForSequenceClassification"),
("ibert", "IBertForSequenceClassification"),
("jamba", "JambaForSequenceClassification"),
("jetmoe", "JetMoeForSequenceClassification"),
Expand Down
1 change: 1 addition & 0 deletions mindone/transformers/models/hunyuan_v1_dense/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
from .modeling_hunyuan_v1_dense import *
Loading