[Auto] Super merge super-merge-example: combined 6 of 10 worktrees

.github/workflows/build_documentation.yml

@@ -11,7 +11,7 @@ on:
 
 jobs:
    build:
-    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3  # main
+    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@2430c1ec91d04667414e2fa31ecfc36c153ea391  # main
     with:
       commit_sha: ${{ github.sha }}
       package: transformers
@@ -23,7 +23,7 @@ jobs:
       hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
 
    build_other_lang:
-    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3  # main
+    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@2430c1ec91d04667414e2fa31ecfc36c153ea391  # main
     with:
       commit_sha: ${{ github.sha }}
       package: transformers

.github/workflows/check_failed_tests.yml

@@ -55,7 +55,7 @@ jobs:
       n_runners: ${{ steps.set-matrix.outputs.n_runners }}
       process: ${{ steps.set-matrix.outputs.process }}
     steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
         continue-on-error: true
         with:
           name: ci_results_${{ inputs.job }}
@@ -127,12 +127,14 @@ jobs:
       image: ${{ inputs.docker }}
       options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
     steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
         with:
           name: ci_results_${{ inputs.job }}
           path: /transformers/ci_results_${{ inputs.job }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
+        env:
+          ACTIONS_ARTIFACT_MAX_ARTIFACT_COUNT: 2000
         with:
           pattern: setup_values*
           path: setup_values
@@ -255,12 +257,14 @@ jobs:
       image: ${{ inputs.docker }}
       options: --gpus all --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
     steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
         with:
           name: ci_results_${{ inputs.job }}
           path: /transformers/ci_results_${{ inputs.job }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
+        env:
+          ACTIONS_ARTIFACT_MAX_ARTIFACT_COUNT: 2000
         with:
           pattern: new_failures_with_bad_commit_${{ inputs.job }}*
           path: /transformers/new_failures_with_bad_commit_${{ inputs.job }}

.github/workflows/model_jobs.yml

@@ -186,7 +186,18 @@ jobs:
         env:
           report_name_prefix: ${{ inputs.report_name_prefix }}
         run: |
-          cat "/transformers/reports/${machine_type}_${report_name_prefix}_${matrix_folders}_test_reports/captured_info.txt"
+          shopt -s nullglob
+          captured_info_files=("/transformers/reports/${machine_type}_${report_name_prefix}_${matrix_folders}_test_reports"/captured_info*.txt)
+
+          if [ ${#captured_info_files[@]} -eq 0 ]; then
+            echo "No captured information files found."
+            exit 0
+          fi
+
+          for captured_info_file in "${captured_info_files[@]}"; do
+            echo "===== ${captured_info_file##*/} ====="
+            cat "$captured_info_file"
+          done
 
       - name: Copy test_outputs.txt
         if: ${{ always() }}

.github/workflows/self-scheduled.yml

@@ -601,7 +601,9 @@ jobs:
       - name: Create output directory
         run: mkdir warnings_in_ci
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
+        env:
+          ACTIONS_ARTIFACT_MAX_ARTIFACT_COUNT: 2000
         with:
           path: warnings_in_ci
 

.github/workflows/slack-report.yml

@@ -55,7 +55,9 @@ jobs:
           # Security: checkout to the `main` branch for untrusted triggers (issue_comment, pull_request_target), otherwise use the specified ref
           ref: ${{ (github.event_name == 'issue_comment' || github.event_name == 'pull_request_target') && 'main' || (inputs.commit_sha || github.sha) }}
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v8
+        env:
+          ACTIONS_ARTIFACT_MAX_ARTIFACT_COUNT: 2000
 
       - name: Prepare some setup values
         run: |

docker/consistency.dockerfile

@@ -5,7 +5,7 @@ ARG REF=main
 RUN apt-get update && apt-get install -y time git g++ pkg-config make git-lfs
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip install uv && uv pip install --no-cache-dir -U pip setuptools GitPython
-RUN uv pip install --no-cache-dir --upgrade 'torch<=2.10.0' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir --upgrade 'torch<=2.11.0' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir pypi-kenlm
 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[quality,testing,torch-speech,vision]"
 RUN git lfs install

docker/custom-tokenizers.dockerfile

@@ -17,7 +17,7 @@ RUN make install -j 10
 
 WORKDIR /
 
-RUN uv pip install --no-cache --upgrade 'torch<=2.10.0' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache --upgrade 'torch<=2.11.0' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir  --no-deps accelerate --extra-index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install  --no-cache-dir "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[ja,testing,sentencepiece,spacy,rjieba]" unidic unidic-lite
 # spacy is not used so not tested. Causes to failures. TODO fix later

docker/examples-torch.dockerfile

@@ -5,7 +5,7 @@ USER root
 RUN apt-get update &&  apt-get install -y --no-install-recommends libsndfile1-dev espeak-ng time git g++ cmake pkg-config openssh-client git-lfs ffmpeg curl
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch<=2.10.0' 'torchaudio' 'torchvision' 'torchcodec<=0.10.0' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch<=2.11.0' 'torchaudio' 'torchvision' 'torchcodec<=0.11.0' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-deps timm accelerate --extra-index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir librosa "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[sklearn,sentencepiece,vision,testing]" seqeval albumentations jiwer
 

docker/exotic-models.dockerfile

@@ -5,7 +5,7 @@ USER root
 RUN apt-get update && apt-get install -y libsndfile1-dev espeak-ng time git libgl1 g++ tesseract-ocr git-lfs curl
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch<=2.10.0' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch<=2.11.0' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir  --no-deps timm accelerate
 RUN uv pip install -U --no-cache-dir pytesseract python-Levenshtein opencv-python nltk
 # RUN uv pip install --no-cache-dir natten==0.15.1+torch210cpu -f https://shi-labs.com/natten/wheels

docker/pipeline-torch.dockerfile

@@ -5,7 +5,7 @@ USER root
 RUN apt-get update &&  apt-get install -y --no-install-recommends libsndfile1-dev espeak-ng time git pkg-config openssh-client git ffmpeg curl
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch<=2.10.0' 'torchaudio' 'torchvision' 'torchcodec<=0.10.0' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch<=2.11.0' 'torchaudio' 'torchvision' 'torchcodec<=0.11.0' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-deps timm accelerate --extra-index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir librosa "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[sklearn,sentencepiece,vision,testing]"
 

docker/torch-light.dockerfile

@@ -5,7 +5,7 @@ USER root
 RUN apt-get update &&  apt-get install -y --no-install-recommends libsndfile1-dev espeak-ng time git g++ cmake pkg-config openssh-client git-lfs ffmpeg curl
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch<=2.10.0' 'torchaudio' 'torchvision' 'torchcodec<=0.10.0' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch<=2.11.0' 'torchaudio' 'torchvision' 'torchcodec<=0.11.0' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-deps timm accelerate --extra-index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir librosa "git+https://github.com/huggingface/transformers.git@${REF}#egg=transformers[sklearn,sentencepiece,vision,testing,tiktoken,num2words,video]"
 

docs/source/en/_toctree.yml

@@ -899,6 +899,8 @@
         title: DAB-DETR
       - local: model_doc/deformable_detr
         title: Deformable DETR
+      - local: model_doc/deimv2
+        title: DEIMv2
       - local: model_doc/deit
         title: DeiT
       - local: model_doc/depth_anything

docs/source/en/model_doc/deimv2.md

@@ -0,0 +1,65 @@
+<!--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 contains specific syntax for our doc-builder (similar to MDX) that may not be
+rendered properly in your Markdown viewer.
+
+-->
+*This model was released on 2025-09-25 and added to Hugging Face Transformers on 2026-04-22.*
+
+# DEIMv2
+
+## Overview
+
+DEIMv2 (DETR with Improved Matching v2) was proposed in [DEIMv2: Real-Time Object Detection Meets DINOv3](https://huggingface.co/papers/2509.20787) by Shihua Huang, Yongjie Hou, Longfei Liu, Xuanlong Yu, and Xi Shen.
+
+The abstract from the paper is the following:
+
+*Driven by the simple and effective Dense O2O, DEIM demonstrates faster convergence and enhanced performance. In this work, we extend it with DINOv3 features, resulting in DEIMv2. DEIMv2 spans eight model sizes from X to Atto, covering GPU, edge, and mobile deployment. For the X, L, M, and S variants, we adopt DINOv3-pretrained / distilled backbones and introduce a Spatial Tuning Adapter (STA), which efficiently converts DINOv3's single-scale output into multi-scale features and complements strong semantics with fine-grained details to enhance detection. For ultra-lightweight models (Nano, Pico, Femto, and Atto), we employ HGNetv2 with depth and width pruning to meet strict resource budgets. Together with a simplified decoder and an upgraded Dense O2O, this unified design enables DEIMv2 to achieve a superior performance-cost trade-off across diverse scenarios, establishing new state-of-the-art results. Notably, our largest model, DEIMv2-X, achieves 57.8 AP with only 50.3M parameters, surpassing prior X-scale models that require over 60M parameters for just 56.5 AP. On the compact side, DEIMv2-S is the first sub-10M model (9.71M) to exceed the 50 AP milestone on COCO, reaching 50.9 AP. Even the ultra-lightweight DEIMv2-Pico, with just 1.5M parameters, delivers 38.5 AP-matching YOLOv10-Nano (2.3M) with ~50% fewer parameters.*
+
+## Usage
+
+```python
+from transformers import AutoImageProcessor, AutoModelForObjectDetection
+from transformers.image_utils import load_image
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = load_image(url)
+
+image_processor = AutoImageProcessor.from_pretrained("harshaljanjani/DEIMv2_HGNetv2_N_COCO_Transformers")
+model = AutoModelForObjectDetection.from_pretrained("harshaljanjani/DEIMv2_HGNetv2_N_COCO_Transformers", device_map="auto")
+
+inputs = image_processor(images=image, return_tensors="pt").to(model.device)
+outputs = model(**inputs)
+
+results = image_processor.post_process_object_detection(
+    outputs, threshold=0.5, target_sizes=[image.size[::-1]]
+)
+
+for result in results:
+    for score, label, box in zip(result["scores"], result["labels"], result["boxes"]):
+        box = [round(i, 2) for i in box.tolist()]
+        print(f"Detected {model.config.id2label[label.item()]} with confidence {round(score.item(), 3)} at location {box}")
+```
+
+## Deimv2Config
+
+[[autodoc]] Deimv2Config
+
+## Deimv2Model
+
+[[autodoc]] Deimv2Model
+    - forward
+
+## Deimv2ForObjectDetection
+
+[[autodoc]] Deimv2ForObjectDetection
+    - forward

docs/source/en/modeling_rules.md

@@ -13,22 +13,22 @@ specific language governing permissions and limitations under the License.
 
 # Model structure rules
 
-Transformers enforces a set of static rules on every `modeling_*.py`, `modular_*.py`, and `configuration_*.py` file. The [mlinter](https://github.com/huggingface/transformers-mlinter) tool checks them as part of `make typing` and errors out if violations are found.
+Transformers enforces a set of static rules on every `modeling_*.py`, `modular_*.py`, and `configuration_*.py` file. The [mlinter](https://github.com/huggingface/transformers-mlinter) package provides the checker engine, and the repository keeps its active rule set in `utils/rules.toml`. That local TOML lets us enable, disable, or tweak rules quickly without waiting for a new `transformers-mlinter` release.
 
 These are the expected model conventions for adding or changing modeling code. They keep the codebase consistent and ensure compatibility with features like pipeline parallelism, device maps, and weight tying.
 
 ## Running the checker
 
-`make typing` runs `mlinter` alongside the `ty` type checker. Run `mlinter` on its own with the following commands.
+`make typing` runs `mlinter` alongside the `ty` type checker through the repo wrapper, so it picks up `utils/rules.toml`. Run the same wrapper directly with the following commands.
 
 ```bash
-mlinter                  # check all modeling files
-mlinter --changed-only   # check only files changed vs origin/main
-mlinter --list-rules     # list all rules and their enabled status
-mlinter --rule TRF001    # show built-in docs for a specific rule
+python utils/check_modeling_structure.py                 # check all modeling files
+python utils/check_modeling_structure.py --changed-only  # check only files changed vs origin/main
+python utils/check_modeling_structure.py --list-rules    # list all rules and their enabled status
+python utils/check_modeling_structure.py --rule TRF001   # show built-in docs for a specific rule
 ```
 
-The `--changed-only` flag is the fastest option during development. It only checks the files you've modified relative to the main branch.
+The `--changed-only` flag is the fastest option during development. It only checks the files you've modified relative to the main branch. If you invoke `mlinter` directly instead of the wrapper, pass `--rules-toml utils/rules.toml` so local overrides are applied.
 
 ## Fixing a violation
 
@@ -52,7 +52,7 @@ Use the rule ID to look up the fix in the [rules reference](#rules-reference). T
 
 ## Rules reference
 
-Each rule below lists what it enforces and a diff showing the fix. Run `mlinter --rule TRF001` to see the built-in docs for any rule.
+Each rule below lists what it enforces and a diff showing the fix. Run `python utils/check_modeling_structure.py --rule TRF001` to see the built-in docs for any rule with the repo's current rule set.
 
 <!-- BEGIN RULES REFERENCE -->