Revert Bamba changes because they're inherited

- Updated 5 models to inherit from CausalLMModelTester and CausalLMModelTest
- Models updated: bamba, biogpt, bloom, codegen, cohere
- Removed redundant methods that are now inherited from base classes
- Added required attributes (base_model_class, causal_lm_class) where needed
- Fixed model-specific issues:
  - CodeGen: Set use_token_type_ids=False to avoid parameter conflicts
  - All models: Removed redundant test methods already in base classes
- All tests passing except bloom's test_bloom_model_past_large_inputs (alibi-specific issue)

.circleci/config.yml

@@ -39,7 +39,7 @@ jobs:
     fetch_tests:
         working_directory: ~/transformers
         docker:
-            - image: huggingface/transformers-quality:dev
+            - image: huggingface/transformers-quality
         parallelism: 1
         steps:
             - checkout
@@ -91,7 +91,7 @@ jobs:
     fetch_all_tests:
         working_directory: ~/transformers
         docker:
-            - image: huggingface/transformers-quality:dev
+            - image: huggingface/transformers-quality
         parallelism: 1
         steps:
             - checkout
@@ -140,7 +140,7 @@ jobs:
     check_code_quality:
         working_directory: ~/transformers
         docker:
-            - image: huggingface/transformers-quality:dev
+            - image: huggingface/transformers-quality
         resource_class: large
         environment:
             TRANSFORMERS_IS_CI: yes
@@ -165,7 +165,7 @@ jobs:
     check_repository_consistency:
         working_directory: ~/transformers
         docker:
-            - image: huggingface/transformers-consistency:dev
+            - image: huggingface/transformers-consistency
         resource_class: large
         environment:
             TRANSFORMERS_IS_CI: yes

.circleci/create_circleci_config.py

@@ -105,10 +105,12 @@ class CircleCIJob:
         else:
             # BIG HACK WILL REMOVE ONCE FETCHER IS UPDATED
             print(os.environ.get("GIT_COMMIT_MESSAGE"))
-            self.docker_image[0]["image"] = f"{self.docker_image[0]['image']}:dev"
+            if "[build-ci-image]" in os.environ.get("GIT_COMMIT_MESSAGE", "") or os.environ.get("GIT_COMMIT_MESSAGE", "") == "dev-ci":
+                self.docker_image[0]["image"] = f"{self.docker_image[0]['image']}:dev"
             print(f"Using {self.docker_image} docker image")
         if self.install_steps is None:
             self.install_steps = ["uv venv && uv pip install ."]
+        self.install_steps.append("uv venv && uv pip install git+https://github.com/ydshieh/pytest.git@8.3.5-ydshieh git+https://github.com/ydshieh/pluggy.git@1.5.0-ydshieh")
         if self.pytest_options is None:
             self.pytest_options = {}
         if isinstance(self.tests_to_run, str):
@@ -212,7 +214,7 @@ generate_job = CircleCIJob(
     docker_image=[{"image": "huggingface/transformers-torch-light"}],
     # networkx==3.3 (after #36957) cause some issues
     # TODO: remove this once it works directly
-    install_steps=["uv venv && uv pip install ."],
+    install_steps=["uv venv && uv pip install . && uv pip install networkx==3.2.1"],
     marker="generate",
     parallelism=6,
 )
@@ -308,7 +310,7 @@ onnx_job = CircleCIJob(
     docker_image=[{"image":"huggingface/transformers-torch-tf-light"}],
     install_steps=[
         "uv venv",
-        "uv pip install .[testing,sentencepiece,onnxruntime,vision,rjieba]",
+        "uv pip install .[torch,tf,testing,sentencepiece,onnxruntime,vision,rjieba]",
     ],
     pytest_options={"k onnx": None},
     pytest_num_workers=1,
@@ -337,7 +339,7 @@ non_model_job = CircleCIJob(
     docker_image=[{"image": "huggingface/transformers-torch-light"}],
     # networkx==3.3 (after #36957) cause some issues
     # TODO: remove this once it works directly
-    install_steps=["uv venv && uv pip install ."],
+    install_steps=["uv venv && uv pip install . && uv pip install networkx==3.2.1"],
     marker="not generate",
     parallelism=6,
 )

.github/workflows/build-ci-docker-images.yml

@@ -3,7 +3,7 @@ name: Build pr ci-docker
 on:
   push:
     branches:
-      - try_torch_2.7_on_circleci_jobs_xxx
+      - push-ci-image # for now let's only build on this branch
   repository_dispatch:
   workflow_call:
     inputs:
@@ -22,6 +22,7 @@ jobs:
   build:
     runs-on: ubuntu-22.04
 
+    if: ${{ contains(github.event.head_commit.message, '[build-ci-image]') || contains(github.event.head_commit.message, '[push-ci-image]') && '!cancelled()' || github.event_name == 'schedule' }}
 
     strategy:
       matrix:
@@ -32,8 +33,13 @@ jobs:
       -
         name: Set tag
         run: |
-          echo "TAG=huggingface/transformers-${{ matrix.file }}:dev" >> "$GITHUB_ENV"
-          echo "setting it to DEV!"
+              if ${{contains(github.event.head_commit.message, '[build-ci-image]')}}; then
+                  echo "TAG=huggingface/transformers-${{ matrix.file }}:dev" >> "$GITHUB_ENV"
+                  echo "setting it to DEV!"
+              else
+                  echo "TAG=huggingface/transformers-${{ matrix.file }}" >> "$GITHUB_ENV"
+
+              fi
       -
         name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
@@ -54,5 +60,18 @@ jobs:
           build-args: |
             REF=${{ github.sha }}
           file: "./docker/${{ matrix.file }}.dockerfile"
-          push: true
+          push: ${{ contains(github.event.head_commit.message, 'ci-image]') ||  github.event_name == 'schedule' }}
           tags: ${{ env.TAG }}
+
+  notify:
+    runs-on: ubuntu-22.04
+    if: ${{ contains(github.event.head_commit.message, '[build-ci-image]') || contains(github.event.head_commit.message, '[push-ci-image]') && '!cancelled()' || github.event_name == 'schedule' }}
+    steps:
+      - name: Post to Slack
+        if: ${{ contains(github.event.head_commit.message, '[push-ci-image]') && github.event_name != 'schedule' }}
+        uses: huggingface/hf-workflows/.github/actions/post-slack@main
+        with:
+          slack_channel: "#transformers-ci-circleci-images"
+          title: 🤗 New docker images for CircleCI are pushed.
+          status: ${{ job.status }}
+          slack_token: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}

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 venv && uv pip install --no-cache-dir -U pip setuptools GitPython
-RUN uv pip install --no-cache-dir --upgrade 'torch' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir --upgrade 'torch==2.6.0' 'torchaudio==2.6.0' 'torchvision==0.21.0' --index-url https://download.pytorch.org/whl/cpu
 # tensorflow pin matching setup.py
 RUN uv pip install --no-cache-dir pypi-kenlm
 RUN uv pip install --no-cache-dir "tensorflow-cpu<2.16" "tf-keras<2.16"

docker/custom-tokenizers.dockerfile

@@ -16,7 +16,7 @@ RUN cmake .. -DCMAKE_INSTALL_PREFIX=/usr/local
 RUN make install -j 10
 
 
-RUN uv pip install --no-cache --upgrade 'torch' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache --upgrade 'torch==2.6.0' --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,jieba,spacy,ftfy,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
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv venv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch==2.6.0' 'torchaudio==2.6.0' 'torchvision==0.21.0' --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
 RUN uv pip uninstall transformers

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-mesa-glx libgl1 g++ tesseract-ocr
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv &&  uv venv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch==2.6.0' 'torchaudio==2.6.0' 'torchvision==0.21.0' --index-url https://download.pytorch.org/whl/cpu
 RUN uv pip install --no-cache-dir  --no-deps timm accelerate
 RUN pip install -U --upgrade-strategy eager --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
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv venv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir --upgrade 'torch==2.6.0' 'torchaudio==2.6.0' 'torchvision==0.21.0' --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]"
 RUN uv pip uninstall transformers

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 git-lfs
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv venv && uv pip install --no-cache-dir -U pip setuptools
-RUN uv pip install --no-cache-dir 'torch' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir --upgrade 'torch==2.6.0' 'torchaudio==2.6.0' 'torchvision==0.21.0' --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]"
 RUN uv pip uninstall transformers

docker/torch-tf-light.dockerfile

@@ -7,7 +7,7 @@ RUN apt-get update &&  apt-get install -y --no-install-recommends libsndfile1-de
 ENV UV_PYTHON=/usr/local/bin/python
 RUN pip --no-cache-dir install uv && uv venv && uv pip install --no-cache-dir -U pip setuptools
 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 'torch' 'torchaudio' 'torchvision' --index-url https://download.pytorch.org/whl/cpu
+RUN uv pip install --no-cache-dir 'torch==2.6.0' 'torchaudio==2.6.0' 'torchvision==0.21.0' --index-url https://download.pytorch.org/whl/cpu
 RUN git lfs install
 
 RUN uv pip install --no-cache-dir pypi-kenlm

docs/source/en/model_doc/gpt_neo.md

@@ -14,94 +14,93 @@ rendered properly in your Markdown viewer.
 
 -->
 
-<div style="float: right;">
-    <div class="flex flex-wrap space-x-1">
-        <img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white">
-        <img alt="Flax" src="https://img.shields.io/badge/Flax-29a79b.svg?style=flat&logo=data:image/png;base64,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
-        ">
-        <img alt="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
-    </div>
+# GPT Neo
+
+<div class="flex flex-wrap space-x-1">
+<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white">
+<img alt="Flax" src="https://img.shields.io/badge/Flax-29a79b.svg?style=flat&logo=data:image/png;base64,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
+">
+<img alt="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
+</div>
+
+## Overview
+
+The GPTNeo model was released in the [EleutherAI/gpt-neo](https://github.com/EleutherAI/gpt-neo) repository by Sid
+Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy. It is a GPT2 like causal language model trained on the
+[Pile](https://pile.eleuther.ai/) dataset.
+
+The architecture is similar to GPT2 except that GPT Neo uses local attention in every other layer with a window size of
+256 tokens.
+
+This model was contributed by [valhalla](https://huggingface.co/valhalla).
+
+## Usage example
+
+The `generate()` method can be used to generate text using GPT Neo model.
+
+```python
+>>> from transformers import GPTNeoForCausalLM, GPT2Tokenizer
+
+>>> model = GPTNeoForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B")
+>>> tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-1.3B")
+
+>>> prompt = (
+...     "In a shocking finding, scientists discovered a herd of unicorns living in a remote, "
+...     "previously unexplored valley, in the Andes Mountains. Even more surprising to the "
+...     "researchers was the fact that the unicorns spoke perfect English."
+... )
+
+>>> input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+
+>>> gen_tokens = model.generate(
+...     input_ids,
+...     do_sample=True,
+...     temperature=0.9,
+...     max_length=100,
+... )
+>>> gen_text = tokenizer.batch_decode(gen_tokens)[0]
+```
+
+## Combining GPT-Neo and Flash Attention 2
+
+First, make sure to install the latest version of Flash Attention 2 to include the sliding window attention feature, and make sure your hardware is compatible with Flash-Attention 2. More details are available [here](https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2) concerning the installation.
+
+Make sure as well to load your model in half-precision (e.g. `torch.float16`).
+
+To load and run a model using Flash Attention 2, refer to the snippet below:
+
+```python
+>>> import torch
+>>> from transformers import AutoModelForCausalLM, AutoTokenizer
+>>> device = "cuda" # the device to load the model onto
+
+>>> model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-neo-2.7B", torch_dtype=torch.float16, attn_implementation="flash_attention_2")
+>>> tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-2.7B")
+
+>>> prompt = "def hello_world():"
+
+>>> model_inputs = tokenizer([prompt], return_tensors="pt").to(device)
+>>> model.to(device)
+
+>>> generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
+>>> tokenizer.batch_decode(generated_ids)[0]
+"def hello_world():\n    >>> run_script("hello.py")\n    >>> exit(0)\n<|endoftext|>"
+```
+
+### Expected speedups
+
+Below is an expected speedup diagram that compares pure inference time between the native implementation in transformers using `EleutherAI/gpt-neo-2.7B` checkpoint and the Flash Attention 2 version of the model.
+Note that for GPT-Neo it is not possible to train / run on very long context as the max [position embeddings](https://huggingface.co/EleutherAI/gpt-neo-2.7B/blob/main/config.json#L58 ) is limited to 2048 - but this is applicable to all gpt-neo models and not specific to FA-2
+
+<div style="text-align: center">
+<img src="https://user-images.githubusercontent.com/49240599/272241893-b1c66b75-3a48-4265-bc47-688448568b3d.png">
 </div>
 
 
-## GPT-Neo
+## Resources
 
-[GPT-Neo](https://zenodo.org/records/5297715) is an open-source alternative to GPT-2 and GPT-3 models, built with Mesh TensorFlow for TPUs. GPT-Neo uses local attention in every other layer for more efficiency. It is trained on the [Pile](https://huggingface.co/datasets/EleutherAI/pile), a diverse dataset consisting of 22 smaller high-quality datasets.
-
-
-You can find all the original GPT-Neo checkpoints under the [EleutherAI](https://huggingface.co/EleutherAI?search_models=gpt-neo) organization.
-
-> [!TIP]
-> Click on the GPT-Neo models in the right sidebar for more examples of how to apply GPT Neo to different language tasks.
-
-The example below demonstrates how to generate text with [`Pipeline`] or the [`AutoModel`], and from the command line.
-
-<hfoptions id="usage">
-<hfoption id="Pipeline">
-
-```py
-import torch
-from transformers import pipeline
-
-pipeline = pipeline(task="text-generation", model="EleutherAI/gpt-neo-1.3B", torch_dtype=torch.float16, device=0)
-pipeline("Hello, I'm a language model")
-```
-</hfoption>
-<hfoption id="AutoModel">
-
-```py
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-neo-1.3B", torch_dtype=torch.float16, device_map="auto", attn_implementation="flash_attention_2")
-tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-1.3B")
-
-input_ids = tokenizer("Hello, I'm a language model", return_tensors="pt").to("cuda")
-
-output = model.generate(**input_ids)
-print(tokenizer.decode(output[0], skip_special_tokens=True))
-```
-
-</hfoption>
-<hfoption id="transformers CLI">
-
-```bash
-echo -e "Hello, I'm a language model" | transformers-cli run --task text-generation --model EleutherAI/gpt-neo-1.3B --device 0
-```
-
-</hfoption>
-</hfoptions>
-
-Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the [Quantization](../quantization/overview) overview for more available quantization backends.
-
-The example below uses [bitsandbytes](../quantization/bitsandbytes) to only quantize the weights to 4-bits.
-
-```py
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype="float16",
-    bnb_4bit_use_double_quant=True
-)
-
-model = AutoModelForCausalLM.from_pretrained(
-    "EleutherAI/gpt-neo-2.7B",
-    quantization_config=quantization_config,
-    device_map="auto"
-)
-
-tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-2.7B")
-inputs = tokenizer("Hello, I'm a language model", return_tensors="pt").to("cuda")
-outputs = model.generate(**inputs, max_new_tokens=100)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
-
-## Notes
-
-- Pad inputs on the right because GPT-Neo uses absolute position embeddings.
+- [Text classification task guide](../tasks/sequence_classification)
+- [Causal language modeling task guide](../tasks/language_modeling)
 
 ## GPTNeoConfig
 

docs/source/en/model_doc/zoedepth.md

@@ -119,11 +119,6 @@ Image.fromarray(depth.astype("uint8"))
 [[autodoc]] ZoeDepthImageProcessor
     - preprocess
 
-## ZoeDepthImageProcessorFast
-
-[[autodoc]] ZoeDepthImageProcessorFast
-    - preprocess
-
 ## ZoeDepthForDepthEstimation
 
 [[autodoc]] ZoeDepthForDepthEstimation

examples/3D_parallel.py

@@ -32,8 +32,8 @@ ocalhost:29504 test_train.py
 
 import logging
 import os
-from collections.abc import Iterable
 from contextlib import nullcontext
+from typing import Iterable
 
 import torch
 import torch.distributed as dist

examples/flax/vision/requirements.txt

@@ -3,6 +3,6 @@ jaxlib>=0.1.59
 flax>=0.3.5
 optax>=0.0.8
 -f https://download.pytorch.org/whl/torch_stable.html
-torch==2.7.1
+torch==2.6.0
 -f https://download.pytorch.org/whl/torch_stable.html
 torchvision==0.12.0+cpu

examples/pytorch/3d_parallel_checks.py

@@ -31,9 +31,8 @@ ocalhost:29504 test_train.py
 
 import logging
 import os
-from collections.abc import Iterable
 from contextlib import nullcontext
-from typing import Dict, Optional
+from typing import Dict, Iterable, Optional
 
 import torch
 import torch.distributed as dist

setup.py

@@ -142,7 +142,6 @@ _deps = [
     "optimum-benchmark>=0.3.0",
     "optuna",
     "optax>=0.0.8,<=0.1.4",
-    "pandas<2.3.0",  # `datasets` requires `pandas` while `pandas==2.3.0` has issues with CircleCI on 2025/06/05
     "packaging>=20.0",
     "parameterized",
     "phonemizer",
@@ -368,7 +367,7 @@ extras["testing"] = (
 
 extras["deepspeed-testing"] = extras["deepspeed"] + extras["testing"] + extras["optuna"] + extras["sentencepiece"]
 extras["ruff"] = deps_list("ruff")
-extras["quality"] = deps_list("datasets", "isort", "ruff", "GitPython", "urllib3", "libcst", "rich", "pandas")
+extras["quality"] = deps_list("datasets", "isort", "ruff", "GitPython", "urllib3", "libcst", "rich")
 
 extras["all"] = (
     extras["tf"]

src/transformers/cache_utils.py

@@ -2,9 +2,8 @@ import copy
 import importlib.metadata
 import json
 import os
-from collections.abc import Iterable
 from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
 
 import torch
 from packaging import version

src/transformers/commands/add_new_model_like.py

@@ -21,8 +21,7 @@ from dataclasses import dataclass
 from datetime import date
 from itertools import chain
 from pathlib import Path
-from re import Pattern
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Any, Callable, Dict, List, Optional, Pattern, Tuple, Union
 
 import yaml
 

src/transformers/data/data_collator.py

@@ -824,7 +824,7 @@ class DataCollatorForLanguageModeling(DataCollatorMixin):
 
     tokenizer: PreTrainedTokenizerBase
     mlm: bool = True
-    mlm_probability: Optional[float] = 0.15
+    mlm_probability: float = 0.15
     mask_replace_prob: float = 0.8
     random_replace_prob: float = 0.1
     pad_to_multiple_of: Optional[int] = None
@@ -833,15 +833,13 @@ class DataCollatorForLanguageModeling(DataCollatorMixin):
     seed: Optional[int] = None
 
     def __post_init__(self):
-        if self.mlm:
-            if self.tokenizer.mask_token is None:
-                raise ValueError(
-                    "This tokenizer does not have a mask token which is necessary for masked language modeling. "
-                    "You should pass `mlm=False` to train on causal language modeling instead."
-                )
-            if self.mlm_probability is None or self.mlm_probability < 0 or self.mlm_probability > 1:
-                raise ValueError("mlm_probability should be between 0 and 1.")
-            self.mlm_probability = float(self.mlm_probability)
+        if self.mlm and self.tokenizer.mask_token is None:
+            raise ValueError(
+                "This tokenizer does not have a mask token which is necessary for masked language modeling. "
+                "You should pass `mlm=False` to train on causal language modeling instead."
+            )
+        if self.mlm_probability < 0 or self.mlm_probability > 1:
+            raise ValueError("mlm_probability should be between 0 and 1.")
         if self.mask_replace_prob + self.random_replace_prob > 1:
             raise ValueError("The sum of mask_replace_prob and random_replace_prob should not exceed 1")
         if self.mask_replace_prob < 0 or self.mask_replace_prob > 1:
@@ -849,6 +847,7 @@ class DataCollatorForLanguageModeling(DataCollatorMixin):
         if self.random_replace_prob < 0 or self.random_replace_prob > 1:
             raise ValueError("random_replace_prob should be between 0 and 1.")
 
+        self.mlm_probability = float(self.mlm_probability)
         self.mask_replace_prob = float(self.mask_replace_prob)
         self.random_replace_prob = float(self.random_replace_prob)
 

src/transformers/dependency_versions_table.py

@@ -48,7 +48,6 @@ deps = {
     "optimum-benchmark": "optimum-benchmark>=0.3.0",
     "optuna": "optuna",
     "optax": "optax>=0.0.8,<=0.1.4",
-    "pandas": "pandas<2.3.0",
     "packaging": "packaging>=20.0",
     "parameterized": "parameterized",
     "phonemizer": "phonemizer",

src/transformers/generation/logits_process.py

@@ -15,8 +15,7 @@
 
 import inspect
 import math
-from collections.abc import Iterable
-from typing import TYPE_CHECKING, Callable, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Callable, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 import torch

src/transformers/models/albert/configuration_albert.py

@@ -16,7 +16,7 @@
 """ALBERT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/aria/image_processing_aria.py

@@ -18,8 +18,7 @@
 # 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 collections.abc import Iterable
-from typing import List, Optional, Tuple, Union
+from typing import Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/aria/modular_aria.py

@@ -12,8 +12,7 @@
 # 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 collections.abc import Iterable
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/auto/auto_factory.py

@@ -442,12 +442,8 @@ class _BaseAutoModelClass:
             else:
                 repo_id = config.name_or_path
             model_class = get_class_from_dynamic_module(class_ref, repo_id, **kwargs)
-            # This block handles the case where the user is loading a model with `trust_remote_code=True`
-            # but a library model exists with the same name. We don't want to override the autoclass
-            # mappings in this case, or all future loads of that model will be the remote code model.
-            if not has_local_code:
-                cls.register(config.__class__, model_class, exist_ok=True)
-                model_class.register_for_auto_class(auto_class=cls)
+            model_class.register_for_auto_class(auto_class=cls)
+            cls.register(config.__class__, model_class, exist_ok=True)
             _ = kwargs.pop("code_revision", None)
             model_class = add_generation_mixin_to_remote_model(model_class)
             return model_class._from_config(config, **kwargs)
@@ -583,12 +579,8 @@ class _BaseAutoModelClass:
                 class_ref, pretrained_model_name_or_path, code_revision=code_revision, **hub_kwargs, **kwargs
             )
             _ = hub_kwargs.pop("code_revision", None)
-            # This block handles the case where the user is loading a model with `trust_remote_code=True`
-            # but a library model exists with the same name. We don't want to override the autoclass
-            # mappings in this case, or all future loads of that model will be the remote code model.
-            if not has_local_code:
-                cls.register(config.__class__, model_class, exist_ok=True)
-                model_class.register_for_auto_class(auto_class=cls)
+            cls.register(config.__class__, model_class, exist_ok=True)
+            model_class.register_for_auto_class(auto_class=cls)
             model_class = add_generation_mixin_to_remote_model(model_class)
             return model_class.from_pretrained(
                 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs

src/transformers/models/auto/image_processing_auto.py

@@ -170,7 +170,7 @@ else:
             ("vitmatte", ("VitMatteImageProcessor", "VitMatteImageProcessorFast")),
             ("xclip", ("CLIPImageProcessor", "CLIPImageProcessorFast")),
             ("yolos", ("YolosImageProcessor", "YolosImageProcessorFast")),
-            ("zoedepth", ("ZoeDepthImageProcessor", "ZoeDepthImageProcessorFast")),
+            ("zoedepth", ("ZoeDepthImageProcessor",)),
         ]
     )
 

src/transformers/models/bart/configuration_bart.py

@@ -16,8 +16,7 @@
 
 import warnings
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer
 from ...configuration_utils import PretrainedConfig

src/transformers/models/beit/configuration_beit.py

@@ -16,7 +16,7 @@
 
 import warnings
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/bert/configuration_bert.py

@@ -16,7 +16,7 @@
 """BERT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/big_bird/configuration_big_bird.py

@@ -15,7 +15,7 @@
 """BigBird model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/bigbird_pegasus/configuration_bigbird_pegasus.py

@@ -15,8 +15,7 @@
 """BigBirdPegasus model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer
 from ...configuration_utils import PretrainedConfig

src/transformers/models/blenderbot/configuration_blenderbot.py

@@ -15,8 +15,7 @@
 """Blenderbot model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer
 from ...configuration_utils import PretrainedConfig

src/transformers/models/blenderbot_small/configuration_blenderbot_small.py

@@ -15,8 +15,7 @@
 """BlenderbotSmall model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer
 from ...configuration_utils import PretrainedConfig

src/transformers/models/bloom/configuration_bloom.py

@@ -15,8 +15,7 @@
 """Bloom configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, List, Optional
+from typing import TYPE_CHECKING, Any, List, Mapping, Optional
 
 from packaging import version
 

src/transformers/models/bridgetower/image_processing_bridgetower.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 """Image processor class for BridgeTower."""
 
-from collections.abc import Iterable
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/bridgetower/image_processing_bridgetower_fast.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 """Fast Image processor class for BridgeTower."""
 
-from collections.abc import Iterable
-from typing import Dict, Optional, Tuple, Union
+from typing import Dict, Iterable, Optional, Tuple, Union
 
 from ...image_processing_utils_fast import (
     BaseImageProcessorFast,

src/transformers/models/camembert/configuration_camembert.py

@@ -16,7 +16,7 @@
 """CamemBERT configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/chinese_clip/configuration_chinese_clip.py

@@ -15,8 +15,7 @@
 """Chinese-CLIP model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any, Mapping, Optional
 
 
 if TYPE_CHECKING:

src/transformers/models/clip/configuration_clip.py

@@ -15,8 +15,7 @@
 """CLIP model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any, Mapping, Optional
 
 
 if TYPE_CHECKING:

src/transformers/models/codegen/configuration_codegen.py

@@ -15,8 +15,7 @@
 """CodeGen model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, List, Optional
+from typing import Any, List, Mapping, Optional
 
 from ... import PreTrainedTokenizer, TensorType, is_torch_available
 from ...configuration_utils import PretrainedConfig

src/transformers/models/conditional_detr/configuration_conditional_detr.py

@@ -15,7 +15,7 @@
 """Conditional DETR model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/conditional_detr/image_processing_conditional_detr.py

@@ -17,8 +17,7 @@
 import io
 import pathlib
 from collections import defaultdict
-from collections.abc import Iterable
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import numpy as np
 

src/transformers/models/convbert/configuration_convbert.py

@@ -15,7 +15,7 @@
 """ConvBERT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/convnext/configuration_convnext.py

@@ -15,7 +15,7 @@
 """ConvNeXT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/data2vec/configuration_data2vec_text.py

@@ -15,7 +15,7 @@
 """Data2VecText configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/data2vec/configuration_data2vec_vision.py

@@ -15,7 +15,7 @@
 """Data2VecVision model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/deberta/configuration_deberta.py

@@ -15,8 +15,7 @@
 """DeBERTa model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional, Union
+from typing import TYPE_CHECKING, Any, Mapping, Optional, Union
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/deberta/modeling_tf_deberta.py

@@ -17,8 +17,7 @@
 from __future__ import annotations
 
 import math
-from collections.abc import Sequence
-from typing import Dict, Optional, Tuple, Union
+from typing import Dict, Optional, Sequence, Tuple, Union
 
 import numpy as np
 import tensorflow as tf

src/transformers/models/deberta_v2/configuration_deberta_v2.py

@@ -15,8 +15,7 @@
 """DeBERTa-v2 model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional, Union
+from typing import TYPE_CHECKING, Any, Mapping, Optional, Union
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/deformable_detr/image_processing_deformable_detr.py

@@ -17,8 +17,7 @@
 import io
 import pathlib
 from collections import defaultdict
-from collections.abc import Iterable
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import numpy as np
 

src/transformers/models/deit/configuration_deit.py

@@ -15,7 +15,7 @@
 """DeiT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/deprecated/deta/image_processing_deta.py

@@ -15,8 +15,7 @@
 """Image processor class for Deformable DETR."""
 
 import pathlib
-from collections.abc import Iterable
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/deprecated/graphormer/collating_graphormer.py

@@ -1,8 +1,7 @@
 # Copyright (c) Microsoft Corporation and HuggingFace
 # Licensed under the MIT License.
 
-from collections.abc import Mapping
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Mapping
 
 import numpy as np
 import torch

src/transformers/models/deprecated/graphormer/modeling_graphormer.py

@@ -15,8 +15,7 @@
 """PyTorch Graphormer model."""
 
 import math
-from collections.abc import Iterable, Iterator
-from typing import List, Optional, Tuple, Union
+from typing import Iterable, Iterator, List, Optional, Tuple, Union
 
 import torch
 import torch.nn as nn

src/transformers/models/deprecated/mega/configuration_mega.py

@@ -15,7 +15,7 @@
 """MEGA configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ....configuration_utils import PretrainedConfig
 from ....onnx import OnnxConfig

src/transformers/models/detr/configuration_detr.py

@@ -15,7 +15,7 @@
 """DETR model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/detr/image_processing_detr.py

@@ -17,8 +17,7 @@
 import io
 import pathlib
 from collections import defaultdict
-from collections.abc import Iterable
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import numpy as np
 

src/transformers/models/dinov2/configuration_dinov2.py

@@ -15,7 +15,7 @@
 """DINOv2 model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/dinov2/modeling_dinov2.py

@@ -491,7 +491,7 @@ class Dinov2PreTrainedModel(PreTrainedModel):
     base_model_prefix = "dinov2"
     main_input_name = "pixel_values"
     supports_gradient_checkpointing = True
-    _no_split_modules = ["Dinov2Layer"]
+    _no_split_modules = ["Dinov2SwiGLUFFN"]
     _supports_sdpa = True
     _supports_flash_attn_2 = True
     _supports_flex_attn = True

src/transformers/models/dinov2_with_registers/modeling_dinov2_with_registers.py

@@ -509,7 +509,7 @@ class Dinov2WithRegistersPreTrainedModel(PreTrainedModel):
     base_model_prefix = "dinov2_with_registers"
     main_input_name = "pixel_values"
     supports_gradient_checkpointing = True
-    _no_split_modules = ["Dinov2WithRegistersLayer"]
+    _no_split_modules = ["Dinov2WithRegistersSwiGLUFFN"]
     _supports_sdpa = True
     _supports_flash_attn_2 = True
     _supports_flex_attn = True

src/transformers/models/distilbert/configuration_distilbert.py

@@ -15,7 +15,7 @@
 """DistilBERT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/dpt/image_processing_dpt.py

@@ -15,8 +15,7 @@
 """Image processor class for DPT."""
 
 import math
-from collections.abc import Iterable
-from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Dict, Iterable, List, Optional, Tuple, Union
 
 from ...utils.import_utils import requires
 

src/transformers/models/efficientnet/configuration_efficientnet.py

@@ -15,8 +15,7 @@
 """EfficientNet model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import List
+from typing import List, Mapping
 
 from packaging import version
 

src/transformers/models/electra/configuration_electra.py

@@ -16,7 +16,7 @@
 """ELECTRA model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/emu3/image_processing_emu3.py

@@ -15,8 +15,7 @@
 # limitations under the License.
 
 import math
-from collections.abc import Iterable
-from typing import Dict, List, Optional, Union
+from typing import Dict, Iterable, List, Optional, Union
 
 import numpy as np
 

src/transformers/models/ernie/configuration_ernie.py

@@ -16,7 +16,7 @@
 """ERNIE model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/esm/modeling_esmfold.py

@@ -14,10 +14,9 @@
 # limitations under the License.
 import math
 import sys
-from collections.abc import Sequence
 from dataclasses import dataclass
 from functools import partial
-from typing import Callable, Dict, List, Optional, Tuple, Union
+from typing import Callable, Dict, List, Optional, Sequence, Tuple, Union
 
 import numpy as np
 import torch

src/transformers/models/esm/openfold_utils/chunk_utils.py

@@ -13,9 +13,8 @@
 # limitations under the License.
 import logging
 import math
-from collections.abc import Iterable, Sequence
 from functools import partial
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Any, Callable, Dict, Iterable, List, Optional, Sequence, Tuple, Union
 
 import torch
 

src/transformers/models/esm/openfold_utils/protein.py

@@ -18,8 +18,7 @@
 import dataclasses
 import re
 import string
-from collections.abc import Iterator, Mapping, Sequence
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, Iterator, List, Mapping, Optional, Sequence, Tuple
 
 import numpy as np
 

src/transformers/models/esm/openfold_utils/residue_constants.py

@@ -18,9 +18,8 @@
 import collections
 import copy
 import functools
-from collections.abc import Mapping, Sequence
 from importlib import resources
-from typing import Dict, List, Tuple
+from typing import Dict, List, Mapping, Sequence, Tuple
 
 import numpy as np
 

src/transformers/models/esm/openfold_utils/rigid_utils.py

@@ -15,9 +15,8 @@
 
 from __future__ import annotations
 
-from collections.abc import Sequence
 from functools import lru_cache
-from typing import Any, Callable, Dict, List, Optional, Tuple
+from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple
 
 import numpy as np
 import torch

src/transformers/models/flaubert/configuration_flaubert.py

@@ -15,7 +15,7 @@
 """Flaubert configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/flava/image_processing_flava.py

@@ -16,9 +16,8 @@
 
 import math
 import random
-from collections.abc import Iterable
 from functools import lru_cache
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/flava/image_processing_flava_fast.py

@@ -16,9 +16,8 @@
 
 import math
 import random
-from collections.abc import Iterable
 from functools import lru_cache
-from typing import Any, Dict, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, Optional, Tuple, Union
 
 from ...image_processing_utils_fast import (
     BaseImageProcessorFast,

src/transformers/models/gpt2/configuration_gpt2.py

@@ -16,8 +16,7 @@
 """OpenAI GPT-2 configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, List, Optional
+from typing import Any, List, Mapping, Optional
 
 from ... import PreTrainedTokenizer, TensorType, is_torch_available
 from ...configuration_utils import PretrainedConfig

src/transformers/models/gpt_neo/configuration_gpt_neo.py

@@ -15,8 +15,7 @@
 """GPT Neo model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer, TensorType, is_torch_available
 from ...configuration_utils import PretrainedConfig

src/transformers/models/gptj/configuration_gptj.py

@@ -15,8 +15,7 @@
 """GPT-J model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, List, Optional
+from typing import Any, List, Mapping, Optional
 
 from ... import PreTrainedTokenizer, TensorType, is_torch_available
 from ...configuration_utils import PretrainedConfig

src/transformers/models/grounding_dino/image_processing_grounding_dino.py

@@ -17,8 +17,7 @@
 import io
 import pathlib
 from collections import defaultdict
-from collections.abc import Iterable
-from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Set, Tuple, Union
+from typing import TYPE_CHECKING, Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import numpy as np
 

src/transformers/models/groupvit/configuration_groupvit.py

@@ -15,8 +15,7 @@
 """GroupViT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any, Mapping, Optional
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/ibert/configuration_ibert.py

@@ -17,7 +17,7 @@
 """I-BERT configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/idefics2/image_processing_idefics2.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 
 
-from collections.abc import Iterable
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/idefics3/image_processing_idefics3.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 
 import math
-from collections.abc import Iterable
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/imagegpt/configuration_imagegpt.py

@@ -15,8 +15,7 @@
 """OpenAI ImageGPT configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any, Mapping, Optional
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/janus/image_processing_janus.py

@@ -19,8 +19,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from collections.abc import Iterable
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/janus/modular_janus.py

@@ -14,9 +14,8 @@
 # limitations under the License.
 
 import copy
-from collections.abc import Iterable
 from dataclasses import dataclass
-from typing import Callable, Dict, List, Optional, Tuple, Union
+from typing import Callable, Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 import torch

src/transformers/models/layoutlm/configuration_layoutlm.py

@@ -15,8 +15,7 @@
 """LayoutLM model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, List, Optional
+from typing import Any, List, Mapping, Optional
 
 from ... import PretrainedConfig, PreTrainedTokenizer
 from ...onnx import OnnxConfig, PatchingSpec

src/transformers/models/layoutlmv3/configuration_layoutlmv3.py

@@ -15,8 +15,7 @@
 """LayoutLMv3 model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any, Mapping, Optional
 
 from packaging import version
 

src/transformers/models/layoutlmv3/image_processing_layoutlmv3.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 """Image processor class for LayoutLMv3."""
 
-from collections.abc import Iterable
-from typing import Dict, Optional, Union
+from typing import Dict, Iterable, Optional, Union
 
 import numpy as np
 

src/transformers/models/levit/configuration_levit.py

@@ -15,7 +15,7 @@
 """LeViT model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
+from typing import Mapping
 
 from packaging import version
 

src/transformers/models/levit/image_processing_levit.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 """Image processor class for LeViT."""
 
-from collections.abc import Iterable
-from typing import Dict, Optional, Union
+from typing import Dict, Iterable, Optional, Union
 
 import numpy as np
 

src/transformers/models/llava_next/image_processing_llava_next.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 """Image processor class for LLaVa-NeXT."""
 
-from collections.abc import Iterable
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/llava_onevision/image_processing_llava_onevision.py

@@ -14,8 +14,7 @@
 # limitations under the License.
 """Image processor class for LLaVa-Onevision."""
 
-from collections.abc import Iterable
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, Iterable, List, Optional, Tuple, Union
 
 import numpy as np
 

src/transformers/models/llava_onevision/processing_llava_onevision.py

@@ -17,8 +17,7 @@ Processor class for LLaVa-Onevision.
 """
 
 import math
-from collections.abc import Iterable
-from typing import List, Union
+from typing import Iterable, List, Union
 
 import numpy as np
 

src/transformers/models/longformer/configuration_longformer.py

@@ -15,8 +15,7 @@
 """Longformer configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import TYPE_CHECKING, Any, List, Optional, Union
+from typing import TYPE_CHECKING, Any, List, Mapping, Optional, Union
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig

src/transformers/models/longt5/configuration_longt5.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 """LongT5 model configuration"""
 
-from collections.abc import Mapping
+from typing import Mapping
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxSeq2SeqConfigWithPast

src/transformers/models/m2m_100/configuration_m2m_100.py

@@ -15,8 +15,7 @@
 """M2M100 model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer
 from ...configuration_utils import PretrainedConfig

src/transformers/models/marian/configuration_marian.py

@@ -15,8 +15,7 @@
 """Marian model configuration"""
 
 from collections import OrderedDict
-from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any, Mapping, Optional
 
 from ... import PreTrainedTokenizer
 from ...configuration_utils import PretrainedConfig

src/transformers/models/mask2former/convert_mask2former_original_pytorch_checkpoint_to_pytorch.py

@@ -15,11 +15,10 @@
 import json
 import sys
 from argparse import ArgumentParser
-from collections.abc import Iterator
 from dataclasses import dataclass
 from pathlib import Path
 from pprint import pformat
-from typing import Any, Dict, List, Set, Tuple
+from typing import Any, Dict, Iterator, List, Set, Tuple
 
 import requests
 import torch

src/transformers/models/mask2former/image_processing_mask2former.py

@@ -15,8 +15,7 @@
 """Image processor class for Mask2Former."""
 
 import math
-from collections.abc import Iterable
-from typing import Any, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import numpy as np
 

src/transformers/models/maskformer/convert_maskformer_original_pytorch_checkpoint_to_pytorch.py

@@ -14,11 +14,10 @@
 # limitations under the License.
 import sys
 from argparse import ArgumentParser
-from collections.abc import Iterator
 from dataclasses import dataclass
 from pathlib import Path
 from pprint import pformat
-from typing import Any, Dict, List, Set, Tuple
+from typing import Any, Dict, Iterator, List, Set, Tuple
 
 import requests
 import torch