Add GlmMoeDsa #43858

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.

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

Merged

Cyrilvallez merged 20 commits into main from glm

Feb 9, 2026

docs/source/en/_toctree.yml

-Original file line number
+Diff line change
@@ Expand Up / @@ -565,6 +565,8 @@ @@
             title: GLM-4.7-Flash
           - local: model_doc/glm_image
             title: GLM-Image
+          - local: model_doc/glm_moe_dsa
+            title: GlmMoeDsa
           - local: model_doc/openai-gpt
             title: GPT
           - local: model_doc/gpt_neo
@@ Expand Down @@

docs/source/en/model_doc/glm_moe_dsa.md

-Original file line number
+Diff line change
@@ -0,0 +1,61 @@
+    <!--Copyright 2026 the HuggingFace Team. All rights reserved.
+    Licensed under the Apache License, Version 2.0 (the "License");
+    you may not use this file except in compliance with the License.
+    You may obtain a copy of the License at
+        http://www.apache.org/licenses/LICENSE-2.0
+    Unless required by applicable law or agreed to in writing, software
+    distributed under the License is distributed on an "AS IS" BASIS,
+    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+    See the License for the specific language governing permissions and
+    limitations under the License.
+    ⚠️ Note that this file is in Markdown but contain specific syntax for our doc-builder (similar to MDX) that may not be rendered properly in your Markdown viewer.
+    -->
+    *This model was released on {release_date} and added to Hugging Face Transformers on 2026-02-08.*
+    # GlmMoeDsa
+    ## Overview
+    The GlmMoeDsa model was proposed in [<INSERT PAPER NAME HERE>](<INSERT PAPER LINK HERE>) by <INSERT AUTHORS HERE>.
+    <INSERT SHORT SUMMARY HERE>
+    The abstract from the paper is the following:
+    <INSERT PAPER ABSTRACT HERE>
+    Tips:
+    <INSERT TIPS ABOUT MODEL HERE>
+    This model was contributed by [INSERT YOUR HF USERNAME HERE](https://huggingface.co/<INSERT YOUR HF USERNAME HERE>).
+    The original code can be found [here](<INSERT LINK TO GITHUB REPO HERE>).
+    ## Usage examples
+    <INSERT SOME NICE EXAMPLES HERE>
+    ## GlmMoeDsaConfig
+    [[autodoc]] GlmMoeDsaConfig
+    ## GlmMoeDsaPreTrainedModel
+    [[autodoc]] GlmMoeDsaPreTrainedModel
+        - forward
+    ## GlmMoeDsaModel
+    [[autodoc]] GlmMoeDsaModel
+        - forward
+    ## GlmMoeDsaForCausalLM
+    [[autodoc]] GlmMoeDsaForCausalLM
+        - forward

src/transformers/conversion_mapping.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -52,6 +52,7 @@ @@
         "ernie4_5_moe": "qwen2_moe",
         "glm4_moe": "qwen2_moe",
         "glm4_moe_lite": "qwen2_moe",
+        "glm_moe_dsa": "qwen2_moe",
         "glm4v_moe": "qwen2_moe",
         "longcat_flash": "qwen2_moe",
         "solar_open": "qwen2_moe",
@@ Expand Down @@

src/transformers/models/__init__.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -158,6 +158,7 @@ @@
         from .glm4v_moe import *
         from .glm46v import *
         from .glm_image import *
+        from .glm_moe_dsa import *
         from .glm_ocr import *
         from .glmasr import *
         from .glpn import *
@@ Expand Down @@

src/transformers/models/auto/configuration_auto.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -186,6 +186,7 @@ @@
             ("glm_image_text", "GlmImageTextConfig"),
             ("glm_image_vision", "GlmImageVisionConfig"),
             ("glm_image_vqmodel", "GlmImageVQVAEConfig"),
+            ("glm_moe_dsa", "GlmMoeDsaConfig"),
             ("glm_ocr", "GlmOcrConfig"),
             ("glm_ocr_text", "GlmOcrTextConfig"),
             ("glm_ocr_vision", "GlmOcrVisionConfig"),
@@ Expand Down Expand Up / @@ -661,6 +662,7 @@ @@
             ("glm_image_text", "GlmImageText"),
             ("glm_image_vision", "GlmImageVisionModel"),
             ("glm_image_vqmodel", "GlmImageVQVAE"),
+            ("glm_moe_dsa", "GlmMoeDsa"),
             ("glm_ocr", "Glmocr"),
             ("glm_ocr_text", "GlmOcrText"),
             ("glm_ocr_vision", "GlmOcrVisionModel"),
@@ Expand Down @@

src/transformers/models/auto/modeling_auto.py

-Original file line number
+Diff line change
@@ Expand Up @@
             ("glm_image_text", "GlmImageTextModel"),
             ("glm_image_vision", "GlmImageVisionModel"),
             ("glm_image_vqmodel", "GlmImageVQVAE"),
+            ("glm_moe_dsa", "GlmMoeDsaModel"),
             ("glm_ocr", "GlmOcrModel"),
             ("glm_ocr_text", "GlmOcrTextModel"),
             ("glm_ocr_vision", "GlmOcrVisionModel"),
@@ Expand Down Expand Up @@
             ("glm4", "Glm4ForCausalLM"),
             ("glm4_moe", "Glm4MoeForCausalLM"),
             ("glm4_moe_lite", "Glm4MoeLiteForCausalLM"),
+            ("glm_moe_dsa", "GlmMoeDsaForCausalLM"),
             ("got_ocr2", "GotOcr2ForConditionalGeneration"),
             ("gpt-sw3", "GPT2LMHeadModel"),
             ("gpt2", "GPT2LMHeadModel"),
@@ Expand Down @@

src/transformers/models/glm_moe_dsa/__init__.py

-Original file line number
+Diff line change
@@ -0,0 +1,28 @@
+    # Copyright 2026 the HuggingFace Team. All rights reserved.
+    #
+    # Licensed under the Apache License, Version 2.0 (the "License");
+    # you may not use this file except in compliance with the License.
+    # You may obtain a copy of the License at
+    #
+    #     http://www.apache.org/licenses/LICENSE-2.0
+    #
+    # Unless required by applicable law or agreed to in writing, software
+    # distributed under the License is distributed on an "AS IS" BASIS,
+    # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+    # See the License for the specific language governing permissions and
+    # limitations under the License.
+    from typing import TYPE_CHECKING
+    from ...utils import _LazyModule
+    from ...utils.import_utils import define_import_structure
+    if TYPE_CHECKING:
+        from .configuration_glm_moe_dsa import *
+        from .modeling_glm_moe_dsa import *
+    else:
+        import sys
+        _file = globals()["__file__"]
+        sys.modules[__name__] = _LazyModule(__name__, _file, define_import_structure(_file), module_spec=__spec__)

Navigation Menu

Uh oh!

Add GlmMoeDsa #43858

Uh oh!

Diff view

Diff view

There are no files selected for viewing

Uh oh!