fix attention mask for flash attention

.circleci/create_circleci_config.py

@@ -30,7 +30,7 @@ COMMON_ENV_VARIABLES = {
     "RUN_PIPELINE_TESTS": False,
 }
 # Disable the use of {"s": None} as the output is way too long, causing the navigation on CircleCI impractical
-COMMON_PYTEST_OPTIONS = {"max-worker-restart": 0, "vvv": None, "rsfE":None}
+COMMON_PYTEST_OPTIONS = {"max-worker-restart": 0, "dist": "loadfile", "vvv": None, "rsfE":None}
 DEFAULT_DOCKER_IMAGE = [{"image": "cimg/python:3.8.12"}]
 
 # Strings that commonly appear in the output of flaky tests when they fail. These are used with `pytest-rerunfailures`
@@ -269,7 +269,6 @@ examples_torch_job = CircleCIJob(
     docker_image=[{"image":"huggingface/transformers-examples-torch"}],
     # TODO @ArthurZucker remove this once docker is easier to build
     install_steps=["uv venv && uv pip install . && uv pip install -r examples/pytorch/_tests_requirements.txt"],
-    pytest_num_workers=4,
 )
 
 
@@ -277,7 +276,6 @@ examples_tensorflow_job = CircleCIJob(
     "examples_tensorflow",
     additional_env={"OMP_NUM_THREADS": 8},
     docker_image=[{"image":"huggingface/transformers-examples-tf"}],
-    pytest_num_workers=2,
 )
 
 

.github/scripts/assign_reviewers.py

@@ -22,16 +22,12 @@ from collections import Counter
 from pathlib import Path
 
 def pattern_to_regex(pattern):
-    if pattern.startswith("/"):
-        start_anchor = True
-        pattern = re.escape(pattern[1:])
-    else:
-        start_anchor = False
-        pattern = re.escape(pattern)
+    start_anchor = pattern.startswith("/")
+    pattern = re.escape(pattern)
     # Replace `*` with "any number of non-slash characters"
     pattern = pattern.replace(r"\*", "[^/]*")
     if start_anchor:
-        pattern = r"^\/?" + pattern  # Allow an optional leading slash after the start of the string
+        pattern = "^" + pattern
     return pattern
 
 def get_file_owners(file_path, codeowners_lines):

.github/workflows/build_pr_documentation.yml

@@ -15,3 +15,4 @@ jobs:
       pr_number: ${{ github.event.number }}
       package: transformers
       languages: ar de en es fr hi it ko pt tr zh ja te
+      custom_container: huggingface/transformers-doc-builder

.github/workflows/change_pr_to_draft.yml

@@ -22,4 +22,4 @@ jobs:
         run: |
           echo $PR_NUMBER
           gh pr ready $PR_NUMBER --repo $REPO --undo
-          gh pr comment $PR_NUMBER --repo $REPO --body "Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the \`Ready for review\` button (at the bottom of the PR page). This will assign reviewers."
+          gh pr comment $PR_NUMBER --repo $REPO --body "Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. When it is ready for review, please click the \`Ready for review\` button (at the bottom of the PR page)."

.github/workflows/push-important-models.yml

@@ -27,7 +27,7 @@ jobs:
 
       - name: Get changed files
         id: changed-files
-        uses: tj-actions/changed-files@1c8e6069583811afb28f97afeaf8e7da80c6be5c
+        uses: tj-actions/changed-files@3f54ebb830831fc121d3263c1857cfbdc310cdb9 #v42
         with:
           files: src/transformers/models/**
 

.github/workflows/self-comment-ci.yml

@@ -29,7 +29,7 @@ jobs:
     runs-on: ubuntu-22.04
     name: Get PR number
     # For security: only allow team members to run
-    if: ${{ github.event.issue.state == 'open' && contains(fromJSON('["ydshieh", "ArthurZucker", "zucchini-nlp", "qubvel", "molbap", "gante", "LysandreJik", "Cyrilvallez", "Rocketknight1", "SunMarc", "muellerzr", "eustlb"]'), github.actor) && (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow')) }}
+    if: ${{ github.event.issue.state == 'open' && contains(fromJSON('["ydshieh", "ArthurZucker", "zucchini-nlp", "qubvel", "molbap", "gante", "LysandreJik", "Cyrilvallez", "Rocketknight1", "SunMarc", "muellerzr"]'), github.actor) && (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow')) }}
     outputs:
       PR_NUMBER: ${{ steps.set_pr_number.outputs.PR_NUMBER }}
     steps:

.github/workflows/self-push-caller.yml

@@ -25,7 +25,7 @@ jobs:
         
         - name: Get changed files
           id: changed-files
-          uses: tj-actions/changed-files@1c8e6069583811afb28f97afeaf8e7da80c6be5c
+          uses: tj-actions/changed-files@v41
         
         - name: Was setup changed 
           id: was_changed
@@ -51,4 +51,4 @@ jobs:
     needs: build-docker-containers
     steps:
       - name: Trigger push CI via workflow_run
-        run: echo "Trigger push CI via workflow_run"
+        run: echo "Trigger push CI via workflow_run"

.github/workflows/update_metdata.yml

@@ -19,7 +19,7 @@ jobs:
       - name: Setup environment
         run: |
           pip install --upgrade pip
-          pip install datasets pandas
+          pip install datasets pandas==2.0.3
           pip install .[torch,tf,flax]
 
       - name: Update metadata

README.md

@@ -25,7 +25,6 @@ limitations under the License.
 </p>
 
 <p align="center">
-    <a href="https://huggingface.com/models"><img alt="Checkpoints on Hub" src="https://img.shields.io/endpoint?url=https://huggingface.co/api/shields/models&color=brightgreen"></a>
     <a href="https://circleci.com/gh/huggingface/transformers"><img alt="Build" src="https://img.shields.io/circleci/build/github/huggingface/transformers/main"></a>
     <a href="https://github.com/huggingface/transformers/blob/main/LICENSE"><img alt="GitHub" src="https://img.shields.io/github/license/huggingface/transformers.svg?color=blue"></a>
     <a href="https://huggingface.co/docs/transformers/index"><img alt="Documentation" src="https://img.shields.io/website/http/huggingface.co/docs/transformers/index.svg?down_color=red&down_message=offline&up_message=online"></a>
@@ -55,254 +54,275 @@ limitations under the License.
 </h4>
 
 <h3 align="center">
-    <p>State-of-the-art pretrained models for inference and training</p>
+    <p>State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow</p>
 </h3>
 
 <h3 align="center">
     <a href="https://hf.co/course"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/course_banner.png"></a>
 </h3>
 
-Transformers is a library of pretrained text, computer vision, audio, video, and multimodal models for inference and training. Use Transformers to fine-tune models on your data, build inference applications, and for generative AI use cases across multiple modalities.
+🤗 Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.
 
-There are over 500K+ Transformers [model checkpoints](https://huggingface.co/models?library=transformers&sort=trending) on the [Hugging Face Hub](https://huggingface.com/models) you can use.
+These models can be applied on:
 
-Explore the [Hub](https://huggingface.com/) today to find a model and use Transformers to help you get started right away.
+* 📝 Text, for tasks like text classification, information extraction, question answering, summarization, translation, and text generation, in over 100 languages.
+* 🖼️ Images, for tasks like image classification, object detection, and segmentation.
+* 🗣️ Audio, for tasks like speech recognition and audio classification.
 
-## Installation
+Transformer models can also perform tasks on **several modalities combined**, such as table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering.
 
-Transformers works with Python 3.9+ [PyTorch](https://pytorch.org/get-started/locally/) 2.0+, [TensorFlow](https://www.tensorflow.org/install/pip) 2.6+, and [Flax](https://flax.readthedocs.io/en/latest/) 0.4.1+.
+🤗 Transformers provides APIs to quickly download and use those pretrained models on a given text, fine-tune them on your own datasets and then share them with the community on our [model hub](https://huggingface.co/models). At the same time, each python module defining an architecture is fully standalone and can be modified to enable quick research experiments.
 
-Create and activate a virtual environment with [venv](https://docs.python.org/3/library/venv.html) or [uv](https://docs.astral.sh/uv/), a fast Rust-based Python package and project manager.
+🤗 Transformers is backed by the three most popular deep learning libraries — [Jax](https://jax.readthedocs.io/en/latest/), [PyTorch](https://pytorch.org/) and [TensorFlow](https://www.tensorflow.org/) — with a seamless integration between them. It's straightforward to train your models with one before loading them for inference with the other.
 
-```py
-# venv
-python -m venv .my-env
-source .my-env/bin/activate
+## Online demos
 
-# uv
-uv venv .my-env
-source .my-env/bin/activate
+You can test most of our models directly on their pages from the [model hub](https://huggingface.co/models). We also offer [private model hosting, versioning, & an inference API](https://huggingface.co/pricing) for public and private models.
+
+Here are a few examples:
+
+In Natural Language Processing:
+- [Masked word completion with BERT](https://huggingface.co/google-bert/bert-base-uncased?text=Paris+is+the+%5BMASK%5D+of+France)
+- [Named Entity Recognition with Electra](https://huggingface.co/dbmdz/electra-large-discriminator-finetuned-conll03-english?text=My+name+is+Sarah+and+I+live+in+London+city)
+- [Text generation with Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
+- [Natural Language Inference with RoBERTa](https://huggingface.co/FacebookAI/roberta-large-mnli?text=The+dog+was+lost.+Nobody+lost+any+animal)
+- [Summarization with BART](https://huggingface.co/facebook/bart-large-cnn?text=The+tower+is+324+metres+%281%2C063+ft%29+tall%2C+about+the+same+height+as+an+81-storey+building%2C+and+the+tallest+structure+in+Paris.+Its+base+is+square%2C+measuring+125+metres+%28410+ft%29+on+each+side.+During+its+construction%2C+the+Eiffel+Tower+surpassed+the+Washington+Monument+to+become+the+tallest+man-made+structure+in+the+world%2C+a+title+it+held+for+41+years+until+the+Chrysler+Building+in+New+York+City+was+finished+in+1930.+It+was+the+first+structure+to+reach+a+height+of+300+metres.+Due+to+the+addition+of+a+broadcasting+aerial+at+the+top+of+the+tower+in+1957%2C+it+is+now+taller+than+the+Chrysler+Building+by+5.2+metres+%2817+ft%29.+Excluding+transmitters%2C+the+Eiffel+Tower+is+the+second+tallest+free-standing+structure+in+France+after+the+Millau+Viaduct)
+- [Question answering with DistilBERT](https://huggingface.co/distilbert/distilbert-base-uncased-distilled-squad?text=Which+name+is+also+used+to+describe+the+Amazon+rainforest+in+English%3F&context=The+Amazon+rainforest+%28Portuguese%3A+Floresta+Amaz%C3%B4nica+or+Amaz%C3%B4nia%3B+Spanish%3A+Selva+Amaz%C3%B3nica%2C+Amazon%C3%ADa+or+usually+Amazonia%3B+French%3A+For%C3%AAt+amazonienne%3B+Dutch%3A+Amazoneregenwoud%29%2C+also+known+in+English+as+Amazonia+or+the+Amazon+Jungle%2C+is+a+moist+broadleaf+forest+that+covers+most+of+the+Amazon+basin+of+South+America.+This+basin+encompasses+7%2C000%2C000+square+kilometres+%282%2C700%2C000+sq+mi%29%2C+of+which+5%2C500%2C000+square+kilometres+%282%2C100%2C000+sq+mi%29+are+covered+by+the+rainforest.+This+region+includes+territory+belonging+to+nine+nations.+The+majority+of+the+forest+is+contained+within+Brazil%2C+with+60%25+of+the+rainforest%2C+followed+by+Peru+with+13%25%2C+Colombia+with+10%25%2C+and+with+minor+amounts+in+Venezuela%2C+Ecuador%2C+Bolivia%2C+Guyana%2C+Suriname+and+French+Guiana.+States+or+departments+in+four+nations+contain+%22Amazonas%22+in+their+names.+The+Amazon+represents+over+half+of+the+planet%27s+remaining+rainforests%2C+and+comprises+the+largest+and+most+biodiverse+tract+of+tropical+rainforest+in+the+world%2C+with+an+estimated+390+billion+individual+trees+divided+into+16%2C000+species)
+- [Translation with T5](https://huggingface.co/google-t5/t5-base?text=My+name+is+Wolfgang+and+I+live+in+Berlin)
+
+In Computer Vision:
+- [Image classification with ViT](https://huggingface.co/google/vit-base-patch16-224)
+- [Object Detection with DETR](https://huggingface.co/facebook/detr-resnet-50)
+- [Semantic Segmentation with SegFormer](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512)
+- [Panoptic Segmentation with Mask2Former](https://huggingface.co/facebook/mask2former-swin-large-coco-panoptic)
+- [Depth Estimation with Depth Anything](https://huggingface.co/docs/transformers/main/model_doc/depth_anything)
+- [Video Classification with VideoMAE](https://huggingface.co/docs/transformers/model_doc/videomae)
+- [Universal Segmentation with OneFormer](https://huggingface.co/shi-labs/oneformer_ade20k_dinat_large)
+
+In Audio:
+- [Automatic Speech Recognition with Whisper](https://huggingface.co/openai/whisper-large-v3)
+- [Keyword Spotting with Wav2Vec2](https://huggingface.co/superb/wav2vec2-base-superb-ks)
+- [Audio Classification with Audio Spectrogram Transformer](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593)
+
+In Multimodal tasks:
+- [Table Question Answering with TAPAS](https://huggingface.co/google/tapas-base-finetuned-wtq)
+- [Visual Question Answering with ViLT](https://huggingface.co/dandelin/vilt-b32-finetuned-vqa)
+- [Image captioning with LLaVa](https://huggingface.co/llava-hf/llava-1.5-7b-hf)
+- [Zero-shot Image Classification with SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384)
+- [Document Question Answering with LayoutLM](https://huggingface.co/impira/layoutlm-document-qa)
+- [Zero-shot Video Classification with X-CLIP](https://huggingface.co/docs/transformers/model_doc/xclip)
+- [Zero-shot Object Detection with OWLv2](https://huggingface.co/docs/transformers/en/model_doc/owlv2)
+- [Zero-shot Image Segmentation with CLIPSeg](https://huggingface.co/docs/transformers/model_doc/clipseg)
+- [Automatic Mask Generation with SAM](https://huggingface.co/docs/transformers/model_doc/sam)
+
+
+## 100 projects using Transformers
+
+Transformers is more than a toolkit to use pretrained models: it's a community of projects built around it and the
+Hugging Face Hub. We want Transformers to enable developers, researchers, students, professors, engineers, and anyone
+else to build their dream projects.
+
+In order to celebrate the 100,000 stars of transformers, we have decided to put the spotlight on the
+community, and we have created the [awesome-transformers](./awesome-transformers.md) page which lists 100
+incredible projects built in the vicinity of transformers.
+
+If you own or use a project that you believe should be part of the list, please open a PR to add it!
+
+## Serious about AI in your organisation? Build faster with the Hugging Face Enterprise Hub.
+
+<a target="_blank" href="https://huggingface.co/enterprise">
+    <img alt="Hugging Face Enterprise Hub" src="https://github.com/user-attachments/assets/247fb16d-d251-4583-96c4-d3d76dda4925">
+</a><br>
+
+## Quick tour
+
+To immediately use a model on a given input (text, image, audio, ...), we provide the `pipeline` API. Pipelines group together a pretrained model with the preprocessing that was used during that model's training. Here is how to quickly use a pipeline to classify positive versus negative texts:
+
+```python
+>>> from transformers import pipeline
+
+# Allocate a pipeline for sentiment-analysis
+>>> classifier = pipeline('sentiment-analysis')
+>>> classifier('We are very happy to introduce pipeline to the transformers repository.')
+[{'label': 'POSITIVE', 'score': 0.9996980428695679}]
 ```
 
-Install Transformers in your virtual environment.
+The second line of code downloads and caches the pretrained model used by the pipeline, while the third evaluates it on the given text. Here, the answer is "positive" with a confidence of 99.97%.
 
-```py
-# pip
-pip install transformers
+Many tasks have a pre-trained `pipeline` ready to go, in NLP but also in computer vision and speech. For example, we can easily extract detected objects in an image:
 
-# uv
-uv pip install transformers
+``` python
+>>> import requests
+>>> from PIL import Image
+>>> from transformers import pipeline
+
+# Download an image with cute cats
+>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png"
+>>> image_data = requests.get(url, stream=True).raw
+>>> image = Image.open(image_data)
+
+# Allocate a pipeline for object detection
+>>> object_detector = pipeline('object-detection')
+>>> object_detector(image)
+[{'score': 0.9982201457023621,
+  'label': 'remote',
+  'box': {'xmin': 40, 'ymin': 70, 'xmax': 175, 'ymax': 117}},
+ {'score': 0.9960021376609802,
+  'label': 'remote',
+  'box': {'xmin': 333, 'ymin': 72, 'xmax': 368, 'ymax': 187}},
+ {'score': 0.9954745173454285,
+  'label': 'couch',
+  'box': {'xmin': 0, 'ymin': 1, 'xmax': 639, 'ymax': 473}},
+ {'score': 0.9988006353378296,
+  'label': 'cat',
+  'box': {'xmin': 13, 'ymin': 52, 'xmax': 314, 'ymax': 470}},
+ {'score': 0.9986783862113953,
+  'label': 'cat',
+  'box': {'xmin': 345, 'ymin': 23, 'xmax': 640, 'ymax': 368}}]
 ```
 
-Install Transformers from source if you want the latest changes in the library or are interested in contributing. However, the *latest* version may not be stable. Feel free to open an [issue](https://github.com/huggingface/transformers/issues) if you encounter an error.
-
-```shell
-git clone https://github.com/huggingface/transformers.git
-cd transformers
-pip install .
-```
-
-## Quickstart
-
-Get started with Transformers right away with the [Pipeline](https://huggingface.co/docs/transformers/pipeline_tutorial) API. The `Pipeline` is a high-level inference class that supports text, audio, vision, and multimodal tasks. It handles preprocessing the input and returns the appropriate output.
-
-Instantiate a pipeline and specify model to use for text generation. The model is downloaded and cached so you can easily reuse it again. Finally, pass some text to prompt the model.
-
-```py
-from transformers import pipeline
-
-pipeline = pipeline(task="text-generation", model="Qwen/Qwen2.5-1.5B")
-pipeline("the secret to baking a really good cake is ")
-[{'generated_text': 'the secret to baking a really good cake is 1) to use the right ingredients and 2) to follow the recipe exactly. the recipe for the cake is as follows: 1 cup of sugar, 1 cup of flour, 1 cup of milk, 1 cup of butter, 1 cup of eggs, 1 cup of chocolate chips. if you want to make 2 cakes, how much sugar do you need? To make 2 cakes, you will need 2 cups of sugar.'}]
-```
-
-To chat with a model, the usage pattern is the same. The only difference is you need to construct a chat history (the input to `Pipeline`) between you and the system.
-
-> [!TIP]
-> You can also chat with a model directly from the command line.
-> ```shell
-> transformers-cli chat --model_name_or_path Qwen/Qwen2.5-0.5B-Instruct
-> ```
-
-```py
-import torch
-from transformers import pipeline
-
-chat = [
-    {"role": "system", "content": "You are a sassy, wise-cracking robot as imagined by Hollywood circa 1986."},
-    {"role": "user", "content": "Hey, can you tell me any fun things to do in New York?"}
-]
-
-pipeline = pipeline(task="text-generation", model="meta-llama/Meta-Llama-3-8B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
-response = pipeline(chat, max_new_tokens=512)
-print(response[0]["generated_text"][-1]["content"])
-```
-
-Expand the examples below to see how `Pipeline` works for different modalities and tasks.
-
-<details>
-<summary>Automatic speech recognition</summary>
-
-```py
-from transformers import pipeline
-
-pipeline = pipeline(task="automatic-speech-recognition", model="openai/whisper-large-v3")
-pipeline("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
-{'text': ' I have a dream that one day this nation will rise up and live out the true meaning of its creed.'}
-```
-
-</details>
-
-<details>
-<summary>Image classification</summary>
+Here, we get a list of objects detected in the image, with a box surrounding the object and a confidence score. Here is the original image on the left, with the predictions displayed on the right:
 
 <h3 align="center">
-    <a><img src="https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png"></a>
+    <a><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png" width="400"></a>
+    <a><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample_post_processed.png" width="400"></a>
 </h3>
 
-```py
-from transformers import pipeline
+You can learn more about the tasks supported by the `pipeline` API in [this tutorial](https://huggingface.co/docs/transformers/task_summary).
 
-pipeline = pipeline(task="image-classification", model="facebook/dinov2-small-imagenet1k-1-layer")
-pipeline("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png")
-[{'label': 'macaw', 'score': 0.997848391532898},
- {'label': 'sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita',
-  'score': 0.0016551691805943847},
- {'label': 'lorikeet', 'score': 0.00018523589824326336},
- {'label': 'African grey, African gray, Psittacus erithacus',
-  'score': 7.85409429227002e-05},
- {'label': 'quail', 'score': 5.502637941390276e-05}]
+In addition to `pipeline`, to download and use any of the pretrained models on your given task, all it takes is three lines of code. Here is the PyTorch version:
+```python
+>>> from transformers import AutoTokenizer, AutoModel
+
+>>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")
+>>> model = AutoModel.from_pretrained("google-bert/bert-base-uncased")
+
+>>> inputs = tokenizer("Hello world!", return_tensors="pt")
+>>> outputs = model(**inputs)
 ```
 
-</details>
+And here is the equivalent code for TensorFlow:
+```python
+>>> from transformers import AutoTokenizer, TFAutoModel
 
-<details>
-<summary>Visual question answering</summary>
+>>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")
+>>> model = TFAutoModel.from_pretrained("google-bert/bert-base-uncased")
 
-
-<h3 align="center">
-    <a><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/idefics-few-shot.jpg"></a>
-</h3>
-
-```py
-from transformers import pipeline
-
-pipeline = pipeline(task="visual-question-answering", model="Salesforce/blip-vqa-base")
-pipeline(
-    image="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/idefics-few-shot.jpg",
-    question="What is in the image?",
-)
-[{'answer': 'statue of liberty'}]
+>>> inputs = tokenizer("Hello world!", return_tensors="tf")
+>>> outputs = model(**inputs)
 ```
 
-</details>
+The tokenizer is responsible for all the preprocessing the pretrained model expects and can be called directly on a single string (as in the above examples) or a list. It will output a dictionary that you can use in downstream code or simply directly pass to your model using the ** argument unpacking operator.
 
-## Why should I use Transformers?
+The model itself is a regular [Pytorch `nn.Module`](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) or a [TensorFlow `tf.keras.Model`](https://www.tensorflow.org/api_docs/python/tf/keras/Model) (depending on your backend) which you can use as usual. [This tutorial](https://huggingface.co/docs/transformers/training) explains how to integrate such a model into a classic PyTorch or TensorFlow training loop, or how to use our `Trainer` API to quickly fine-tune on a new dataset.
+
+## Why should I use transformers?
 
 1. Easy-to-use state-of-the-art models:
-    - High performance on natural language understanding & generation, computer vision, audio, video, and multimodal tasks.
-    - Low barrier to entry for researchers, engineers, and developers.
+    - High performance on natural language understanding & generation, computer vision, and audio tasks.
+    - Low barrier to entry for educators and practitioners.
     - Few user-facing abstractions with just three classes to learn.
     - A unified API for using all our pretrained models.
 
 1. Lower compute costs, smaller carbon footprint:
-    - Share trained models instead of training from scratch.
-    - Reduce compute time and production costs.
-    - Dozens of model architectures with 1M+ pretrained checkpoints across all modalities.
+    - Researchers can share trained models instead of always retraining.
+    - Practitioners can reduce compute time and production costs.
+    - Dozens of architectures with over 400,000 pretrained models across all modalities.
 
-1. Choose the right framework for every part of a models lifetime:
+1. Choose the right framework for every part of a model's lifetime:
     - Train state-of-the-art models in 3 lines of code.
-    - Move a single model between PyTorch/JAX/TF2.0 frameworks at will.
-    - Pick the right framework for training, evaluation, and production.
+    - Move a single model between TF2.0/PyTorch/JAX frameworks at will.
+    - Seamlessly pick the right framework for training, evaluation, and production.
 
 1. Easily customize a model or an example to your needs:
     - We provide examples for each architecture to reproduce the results published by its original authors.
     - Model internals are exposed as consistently as possible.
     - Model files can be used independently of the library for quick experiments.
 
-<a target="_blank" href="https://huggingface.co/enterprise">
-    <img alt="Hugging Face Enterprise Hub" src="https://github.com/user-attachments/assets/247fb16d-d251-4583-96c4-d3d76dda4925">
-</a><br>
-
-## Why shouldn't I use Transformers?
+## Why shouldn't I use transformers?
 
 - This library is not a modular toolbox of building blocks for neural nets. The code in the model files is not refactored with additional abstractions on purpose, so that researchers can quickly iterate on each of the models without diving into additional abstractions/files.
-- The training API is optimized to work with PyTorch models provided by Transformers. For generic machine learning loops, you should use another library like [Accelerate](https://huggingface.co/docs/accelerate).
-- The [example scripts]((https://github.com/huggingface/transformers/tree/main/examples)) are only *examples*. They may not necessarily work out-of-the-box on your specific use case and you'll need to adapt the code for it to work.
+- The training API is not intended to work on any model but is optimized to work with the models provided by the library. For generic machine learning loops, you should use another library (possibly, [Accelerate](https://huggingface.co/docs/accelerate)).
+- While we strive to present as many use cases as possible, the scripts in our [examples folder](https://github.com/huggingface/transformers/tree/main/examples) are just that: examples. It is expected that they won't work out-of-the-box on your specific problem and that you will be required to change a few lines of code to adapt them to your needs.
 
-## 100 projects using Transformers
+## Installation
 
-Transformers is more than a toolkit to use pretrained models, it's a community of projects built around it and the
-Hugging Face Hub. We want Transformers to enable developers, researchers, students, professors, engineers, and anyone
-else to build their dream projects.
+### With pip
 
-In order to celebrate Transformers 100,000 stars, we wanted to put the spotlight on the
-community with the [awesome-transformers](./awesome-transformers.md) page which lists 100
-incredible projects built with Transformers.
+This repository is tested on Python 3.9+, Flax 0.4.1+, PyTorch 2.0+, and TensorFlow 2.6+.
 
-If you own or use a project that you believe should be part of the list, please open a PR to add it!
+You should install 🤗 Transformers in a [virtual environment](https://docs.python.org/3/library/venv.html). If you're unfamiliar with Python virtual environments, check out the [user guide](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/).
 
-## Example models
+First, create a virtual environment with the version of Python you're going to use and activate it.
 
-You can test most of our models directly on their [Hub model pages](https://huggingface.co/models).
+**macOS/Linux**
 
-Expand each modality below to see a few example models for various use cases.
+```python -m venv env
+source env/bin/activate
+```
 
-<details>
-<summary>Audio</summary>
+**Windows**
 
-- Audio classification with [Whisper](https://huggingface.co/openai/whisper-large-v3-turbo)
-- Automatic speech recognition with [Moonshine](https://huggingface.co/UsefulSensors/moonshine)
-- Keyword spotting with [Wav2Vec2](https://huggingface.co/superb/wav2vec2-base-superb-ks)
-- Speech to speech generation with [Moshi](https://huggingface.co/kyutai/moshiko-pytorch-bf16)
-- Text to audio with [MusicGen](https://huggingface.co/facebook/musicgen-large)
-- Text to speech with [Bark](https://huggingface.co/suno/bark)
+``` python -m venv env
+env\Scripts\activate
+```
 
-</details>
+To use 🤗 Transformers, you must install at least one of Flax, PyTorch, or TensorFlow. Refer to the official installation guides for platform-specific commands:
 
-<details>
-<summary>Computer vision</summary>
+[TensorFlow installation page](https://www.tensorflow.org/install/), 
+[PyTorch installation page](https://pytorch.org/get-started/locally/#start-locally) and/or [Flax](https://github.com/google/flax#quick-install) and [Jax](https://github.com/google/jax#installation) 
 
-- Automatic mask generation with [SAM](https://huggingface.co/facebook/sam-vit-base)
-- Depth estimation with [DepthPro](https://huggingface.co/apple/DepthPro-hf)
-- Image classification with [DINO v2](https://huggingface.co/facebook/dinov2-base)
-- Keypoint detection with [SuperGlue](https://huggingface.co/magic-leap-community/superglue_outdoor)
-- Keypoint matching with [SuperGlue](https://huggingface.co/magic-leap-community/superglue)
-- Object detection with [RT-DETRv2](https://huggingface.co/PekingU/rtdetr_v2_r50vd)
-- Pose Estimation with [VitPose](https://huggingface.co/usyd-community/vitpose-base-simple)
-- Universal segmentation with [OneFormer](https://huggingface.co/shi-labs/oneformer_ade20k_swin_large)
-- Video classification with [VideoMAE](https://huggingface.co/MCG-NJU/videomae-large)
+When one of those backends has been installed, 🤗 Transformers can be installed using pip as follows:
 
-</details>
+```
+pip install transformers
+```
 
-<details>
-<summary>Multimodal</summary>
+If you'd like to play with the examples or need the bleeding edge of the code and can't wait for a new release, you must [install the library from source](https://huggingface.co/docs/transformers/installation#installing-from-source).
 
-- Audio or text to text with [Qwen2-Audio](https://huggingface.co/Qwen/Qwen2-Audio-7B)
-- Document question answering with [LayoutLMv3](https://huggingface.co/microsoft/layoutlmv3-base)
-- Image or text to text with [Qwen-VL](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
-- Image captioning [BLIP-2](https://huggingface.co/Salesforce/blip2-opt-2.7b)
-- OCR-based document understanding with [GOT-OCR2](https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf)
-- Table question answering with [TAPAS](https://huggingface.co/google/tapas-base)
-- Unified multimodal understanding and generation with [Emu3](https://huggingface.co/BAAI/Emu3-Gen)
-- Vision to text with [Llava-OneVision](https://huggingface.co/llava-hf/llava-onevision-qwen2-0.5b-ov-hf)
-- Visual question answering with [Llava](https://huggingface.co/llava-hf/llava-1.5-7b-hf)
-- Visual referring expression segmentation with [Kosmos-2](https://huggingface.co/microsoft/kosmos-2-patch14-224)
+```
+git clone https://github.com/huggingface/transformers.git
+cd transformers
+pip install .
+```
 
-</details>
+### With conda
 
-<details>
-<summary>NLP</summary>
+🤗 Transformers can be installed using conda as follows:
 
-- Masked word completion with [ModernBERT](https://huggingface.co/answerdotai/ModernBERT-base)
-- Named entity recognition with [Gemma](https://huggingface.co/google/gemma-2-2b)
-- Question answering with [Mixtral](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1)
-- Summarization with [BART](https://huggingface.co/facebook/bart-large-cnn)
-- Translation with [T5](https://huggingface.co/google-t5/t5-base)
-- Text generation with [Llama](https://huggingface.co/meta-llama/Llama-3.2-1B)
-- Text classification with [Qwen](https://huggingface.co/Qwen/Qwen2.5-0.5B)
+```shell script
+conda install conda-forge::transformers
+```
 
-</details>
+> **_NOTE:_** Installing `transformers` from the `huggingface` channel is deprecated.
+
+Follow the installation pages of Flax, PyTorch or TensorFlow to see how to install them with conda.
+
+> **_NOTE:_**  On Windows, you may be prompted to activate Developer Mode in order to benefit from caching. If this is not an option for you, please let us know in [this issue](https://github.com/huggingface/huggingface_hub/issues/1062).
+
+## Model architectures
+
+**[All the model checkpoints](https://huggingface.co/models)** provided by 🤗 Transformers are seamlessly integrated from the huggingface.co [model hub](https://huggingface.co/models), where they are uploaded directly by [users](https://huggingface.co/users) and [organizations](https://huggingface.co/organizations).
+
+Current number of checkpoints: ![](https://img.shields.io/endpoint?url=https://huggingface.co/api/shields/models&color=brightgreen)
+
+🤗 Transformers currently provides the following architectures: see [here](https://huggingface.co/docs/transformers/model_summary) for a high-level summary of each them.
+
+To check if each model has an implementation in Flax, PyTorch or TensorFlow, or has an associated tokenizer backed by the 🤗 Tokenizers library, refer to [this table](https://huggingface.co/docs/transformers/index#supported-frameworks).
+
+These implementations have been tested on several datasets (see the example scripts) and should match the performance of the original implementations. You can find more details on performance in the Examples section of the [documentation](https://github.com/huggingface/transformers/tree/main/examples).
+
+
+## Learn more
+
+| Section | Description |
+|-|-|
+| [Documentation](https://huggingface.co/docs/transformers/) | Full API documentation and tutorials |
+| [Task summary](https://huggingface.co/docs/transformers/task_summary) | Tasks supported by 🤗 Transformers |
+| [Preprocessing tutorial](https://huggingface.co/docs/transformers/preprocessing) | Using the `Tokenizer` class to prepare data for the models |
+| [Training and fine-tuning](https://huggingface.co/docs/transformers/training) | Using the models provided by 🤗 Transformers in a PyTorch/TensorFlow training loop and the `Trainer` API |
+| [Quick tour: Fine-tuning/usage scripts](https://github.com/huggingface/transformers/tree/main/examples) | Example scripts for fine-tuning models on a wide range of tasks |
+| [Model sharing and uploading](https://huggingface.co/docs/transformers/model_sharing) | Upload and share your fine-tuned models with the community |
 
 ## Citation
 

docker/transformers-quantization-latest-gpu/Dockerfile

@@ -79,9 +79,6 @@ RUN git clone https://github.com/NetEase-FuXi/EETQ.git && cd EETQ/ && git submod
 # Add compressed-tensors for quantization testing
 RUN python3 -m pip install --no-cache-dir compressed-tensors
 
-# Add AMD Quark for quantization testing
-RUN python3 -m pip install --no-cache-dir amd-quark
-
 # Add transformers in editable mode
 RUN python3 -m pip install --no-cache-dir -e ./transformers[dev-torch]
 

docs/source/de/quicktour.md

@@ -156,7 +156,7 @@ Die [`pipeline`] kann jedes Modell aus dem [Model Hub](https://huggingface.co/mo
 
 <frameworkcontent>
 <pt>
-Use the [`AutoModelForSequenceClassification`] and [`AutoTokenizer`] to load the pretrained model and its associated tokenizer (more on an `AutoClass` below):
+Use the [`AutoModelForSequenceClassification`] and [`AutoTokenizer`] to load the pretrained model and it's associated tokenizer (more on an `AutoClass` below):
 
 ```py
 >>> from transformers import AutoTokenizer, AutoModelForSequenceClassification
@@ -166,7 +166,7 @@ Use the [`AutoModelForSequenceClassification`] and [`AutoTokenizer`] to load the
 ```
 </pt>
 <tf>
-Use the [`TFAutoModelForSequenceClassification`] and [`AutoTokenizer`] to load the pretrained model and its associated tokenizer (more on an `TFAutoClass` below):
+Use the [`TFAutoModelForSequenceClassification`] and [`AutoTokenizer`] to load the pretrained model and it's associated tokenizer (more on an `TFAutoClass` below):
 
 ```py
 >>> from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
@@ -222,7 +222,7 @@ Anschließend wandelt der Tokenizer die Token in Zahlen um, um einen Tensor als
 Der Tokenizer gibt ein Wörterbuch zurück, das Folgendes enthält:
 
 * [input_ids](./glossary#input-ids): numerische Repräsentationen Ihrer Token.
-* [attention_mask](.glossary#attention-mask): gibt an, welche Token beachtet werden sollen.
+* [atttention_mask](.glossary#attention-mask): gibt an, welche Token beachtet werden sollen.
 
 Genau wie die [`pipeline`] akzeptiert der Tokenizer eine Liste von Eingaben. Darüber hinaus kann der Tokenizer den Text auch auffüllen und kürzen, um einen Stapel mit einheitlicher Länge zurückzugeben:
 

docs/source/en/_toctree.yml

@@ -187,8 +187,6 @@
     title: Optimum
   - local: quantization/quanto
     title: Quanto
-  - local: quantization/quark
-    title: Quark
   - local: quantization/torchao
     title: torchao
   - local: quantization/spqr
@@ -531,8 +529,6 @@
         title: MegatronGPT2
       - local: model_doc/mistral
         title: Mistral
-      - local: model_doc/mistral3
-        title: Mistral3
       - local: model_doc/mixtral
         title: Mixtral
       - local: model_doc/mluke
@@ -583,8 +579,6 @@
         title: Phi
       - local: model_doc/phi3
         title: Phi-3
-      - local: model_doc/phi4_multimodal
-        title: Phi4 Multimodal
       - local: model_doc/phimoe
         title: PhiMoE
       - local: model_doc/phobert
@@ -737,8 +731,6 @@
         title: NAT
       - local: model_doc/poolformer
         title: PoolFormer
-      - local: model_doc/prompt_depth_anything
-        title: Prompt Depth Anything
       - local: model_doc/pvt
         title: Pyramid Vision Transformer (PVT)
       - local: model_doc/pvt_v2
@@ -987,8 +979,6 @@
         title: Qwen2VL
       - local: model_doc/sam
         title: Segment Anything
-      - local: model_doc/shieldgemma2
-        title: ShieldGemma2
       - local: model_doc/siglip
         title: SigLIP
       - local: model_doc/siglip2
@@ -1048,8 +1038,6 @@
   - sections:
     - local: internal/modeling_utils
       title: Custom Layers and Utilities
-    - local: internal/model_debugging_utils
-      title: Utilities for Model Debugging
     - local: internal/pipelines_utils
       title: Utilities for pipelines
     - local: internal/tokenization_utils

docs/source/en/cache_explanation.md

@@ -9,7 +9,7 @@ Unless required by applicable law or agreed to in writing, software distributed
 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
+⚠️ 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.
 
 -->
@@ -62,7 +62,7 @@ for _ in range(max_new_tokens):
     # Greedily sample one next token
     next_token_ids = outputs.logits[:, -1:].argmax(-1)
     generated_ids = torch.cat([generated_ids, next_token_ids], dim=-1)
-    # Prepare inputs for the next generation step by leaving unprocessed tokens, in our case we have only one new token
+    # Prepare inputs for the next generation step by leaaving unprocessed tokens, in our case we have only one new token
     # and expanding attn mask for the new token, as explained above
     attention_mask = inputs["attention_mask"]
     attention_mask = torch.cat([attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1)
@@ -88,7 +88,7 @@ model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", to
 inputs = tokenizer("Hello, my name is", return_tensors="pt").to(model.device)
 
 # `return_dict_in_generate=True` is required to return the cache and `return_legacy_cache` forces the returned cache
-# in the legacy format
+# in the the legacy format
 generation_outputs = model.generate(**inputs, return_dict_in_generate=True, return_legacy_cache=True, max_new_tokens=5)
 
 cache = DynamicCache.from_legacy_cache(generation_outputs.past_key_values)

docs/source/en/chat_templating_multimodal.md

@@ -9,7 +9,7 @@ Unless required by applicable law or agreed to in writing, software distributed
 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
+⚠️ 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.
 
 -->
@@ -18,7 +18,7 @@ rendered properly in your Markdown viewer.
 
 Multimodal model chat templates expect a similar [template](./chat_templating) as text-only models. It needs `messages` that includes a dictionary of the `role` and `content`.
 
-Multimodal templates are included in the [Processor](./processors) class and require an additional `type` key for specifying whether the included content is an image, video, or text.
+Multimodal templates are included in the [Processor](./processors) class and requires an additional `type` key for specifying whether the included content is an image, video, or text.
 
 This guide will show you how to format chat templates for multimodal models as well as some best practices for configuring the template
 
@@ -109,7 +109,7 @@ These inputs are now ready to be used in [`~GenerationMixin.generate`].
 
 Some vision models also support video inputs. The message format is very similar to the format for [image inputs](#image-inputs).
 
-- The content `"type"` should be `"video"` to indicate the content is a video.
+- The content `"type"` should be `"video"` to indicate the the content is a video.
 - For videos, it can be a link to the video (`"url"`) or it could be a file path (`"path"`). Videos loaded from a URL can only be decoded with [PyAV](https://pyav.basswood-io.com/docs/stable/) or [Decord](https://github.com/dmlc/decord).
 
 > [!WARNING]
@@ -141,7 +141,7 @@ Pass `messages` to [`~ProcessorMixin.apply_chat_template`] to tokenize the input
 
 The `video_load_backend` parameter refers to a specific framework to load a video. It supports [PyAV](https://pyav.basswood-io.com/docs/stable/), [Decord](https://github.com/dmlc/decord), [OpenCV](https://github.com/opencv/opencv), and [torchvision](https://pytorch.org/vision/stable/index.html).
 
-The examples below use Decord as the backend because it is a bit faster than PyAV.
+The examples below uses Decord as the backend because it is a bit faster than PyAV.
 
 <hfoptions id="sampling">
 <hfoption id="fixed number of frames">

docs/source/en/custom_models.md

@@ -131,7 +131,7 @@ class ResnetModel(PreTrainedModel):
 </hfoption>
 <hfoption id="ResnetModelForImageClassification">
 
-The `forward` method needs to be rewritten to calculate the loss for each logit if labels are available. Otherwise, the ResNet model class is the same.
+The `forward` method needs to be rewrittten to calculate the loss for each logit if labels are available. Otherwise, the ResNet model class is the same.
 
 > [!TIP]
 > Add `config_class` to the model class to enable [AutoClass](#autoclass-support) support.

docs/source/en/gpu_selection.md

@@ -9,7 +9,7 @@ Unless required by applicable law or agreed to in writing, software distributed
 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
+⚠️ 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.
 
 -->
@@ -56,7 +56,7 @@ deepspeed --num_gpus 2 trainer-program.py ...
 
 ### Order of GPUs
 
-To select specific GPUs to use and their order, configure the `CUDA_VISIBLE_DEVICES` environment variable. It is easiest to set the environment variable in `~/bashrc` or another startup config file. `CUDA_VISIBLE_DEVICES` is used to map which GPUs are used. For example, if there are 4 GPUs (0, 1, 2, 3) and you only want to run GPUs 0 and 2:
+To select specific GPUs to use and their order, configure the the `CUDA_VISIBLE_DEVICES` environment variable. It is easiest to set the environment variable in `~/bashrc` or another startup config file. `CUDA_VISIBLE_DEVICES` is used to map which GPUs are used. For example, if there are 4 GPUs (0, 1, 2, 3) and you only want to run GPUs 0 and 2:
 
 ```bash
 CUDA_VISIBLE_DEVICES=0,2 torchrun trainer-program.py ...

docs/source/en/installation.md

@@ -20,7 +20,7 @@ rendered properly in your Markdown viewer.
 
 # Installation
 
-Transformers works with [PyTorch](https://pytorch.org/get-started/locally/), [TensorFlow 2.0](https://www.tensorflow.org/install/pip), and [Flax](https://flax.readthedocs.io/en/latest/). It has been tested on Python 3.9+, PyTorch 2.0+, TensorFlow 2.6+, and Flax 0.4.1+.
+Transformers works with [PyTorch](https://pytorch.org/get-started/locally/), [TensorFlow 2.0](https://www.tensorflow.org/install/pip), and [Flax](https://flax.readthedocs.io/en/latest/). It has been tested on Python 3.6+, PyTorch 1.1.0+, TensorFlow 2.0+, and Flax.
 
 ## Virtual environment
 
@@ -33,7 +33,7 @@ Create and activate a virtual environment in your project directory with [venv](
 
 ```bash
 python -m venv .env
-source .env/bin/activate
+source ./env/bin/activate
 ```
 
 </hfoption>
@@ -43,7 +43,7 @@ source .env/bin/activate
 
 ```bash
 uv venv .env
-source .env/bin/activate
+source ./env/bin/activate
 ```
 
 </hfoption>

docs/source/en/internal/model_debugging_utils.md

@@ -1,71 +0,0 @@
-<!--Copyright 2025 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.
-
--->
-
-# Model debugging toolboxes
-
-This page lists all the debugging and model adding tools used by the library, as well as the utility functions it provides for it.
-
-Most of those are only useful if you are adding new models in the library.
-
-
-## Model addition debuggers
-
-
-### Model addition debugger - context manager for model adders
-
-This context manager is a power user tool intended for model adders.
-It tracks all forward calls within a model forward and logs a slice of each input and output on a nested Json.
-To note, this context manager enforces `torch.inference_mode()`.
-
-### Rationale
-
-Because when porting models to transformers, even from python to python, model adders often have to do a lot of manual operations, involving saving and loading tensors, comparing dtypes, etc. This small tool can hopefully shave off some time.
-
-### Usage
-
-Add this context manager as follows to debug a model:
-
-```python
-import torch
-from PIL import Image
-import requests
-from transformers import LlavaProcessor, LlavaForConditionalGeneration
-torch.random.manual_seed(673)
-
-# load pretrained model and processor
-model_id = "llava-hf/llava-1.5-7b-hf"
-processor = LlavaProcessor.from_pretrained(model_id)
-model = LlavaForConditionalGeneration.from_pretrained(model_id, low_cpu_mem_usage=True)
-
-# create random image input
-random_image = Image.fromarray(torch.randint(0, 256, (224, 224, 3), dtype=torch.uint8).numpy())
-
-# prompt
-prompt = "<image>Describe this image."
-
-# process inputs
-inputs = processor(text=prompt, images=random_image, return_tensors="pt")
-
-# call forward method (not .generate!)
-with model_addition_debugger_context(model, "optional_path_to_your_output_file.json"):
-    output = model.forward(**inputs)
-
-```
-
-
-[[autodoc]] model_addition_debugger
-
-[[autodoc]] model_addition_debugger_context

docs/source/en/main_classes/optimizer_schedules.md

@@ -22,6 +22,9 @@ The `.optimization` module provides:
 - several schedules in the form of schedule objects that inherit from `_LRSchedule`:
 - a gradient accumulation class to accumulate the gradients of multiple batches
 
+## AdamW (PyTorch)
+
+[[autodoc]] AdamW
 
 ## AdaFactor (PyTorch)
 

docs/source/en/main_classes/quantization.md

@@ -88,7 +88,3 @@ Learn how to quantize models in the [Quantization](../quantization) guide.
 ## FineGrainedFP8Config
 
 [[autodoc]] FineGrainedFP8Config
-
-## QuarkConfig
-
-[[autodoc]] QuarkConfig

docs/source/en/model_doc/audio-spectrogram-transformer.md

@@ -18,7 +18,6 @@ rendered properly in your Markdown viewer.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/bert.md

@@ -14,85 +14,159 @@ 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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&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="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
-    </div>
-</div>
-
 # BERT
 
-[BERT](https://huggingface.co/papers/1810.04805) is a bidirectional transformer pretrained on unlabeled text to predict masked tokens in a sentence and to predict whether one sentence follows another. The main idea is that by randomly masking some tokens, the model can train on text to the left and right, giving it a more thorough understanding. BERT is also very versatile because its learned language representations can be adapted for other NLP tasks by fine-tuning an additional layer or head.
+<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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&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="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
+</div>
 
-You can find all the original BERT checkpoints under the [BERT](https://huggingface.co/collections/google/bert-release-64ff5e7a4be99045d1896dbc) collection.
+## Overview
 
-> [!TIP]
-> Click on the BERT models in the right sidebar for more examples of how to apply BERT to different language tasks.
+The BERT model was proposed in [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://arxiv.org/abs/1810.04805) by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova. It's a
+bidirectional transformer pretrained using a combination of masked language modeling objective and next sentence
+prediction on a large corpus comprising the Toronto Book Corpus and Wikipedia.
 
-The example below demonstrates how to predict the `[MASK]` token with [`Pipeline`], [`AutoModel`], and from the command line.
+The abstract from the paper is the following:
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+*We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations
+from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional
+representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result,
+the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models
+for a wide range of tasks, such as question answering and language inference, without substantial task-specific
+architecture modifications.*
 
-```py
-import torch
-from transformers import pipeline
+*BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural
+language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI
+accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute
+improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).*
 
-pipeline = pipeline(
-    task="fill-mask",
-    model="google-bert/bert-base-uncased",
-    torch_dtype=torch.float16,
-    device=0
-)
-pipeline("Plants create [MASK] through a process known as photosynthesis.")
+This model was contributed by [thomwolf](https://huggingface.co/thomwolf). The original code can be found [here](https://github.com/google-research/bert).
+
+## Usage tips
+
+- BERT is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than
+  the left.
+- BERT was trained with the masked language modeling (MLM) and next sentence prediction (NSP) objectives. It is
+  efficient at predicting masked tokens and at NLU in general, but is not optimal for text generation.
+- Corrupts the inputs by using random masking, more precisely, during pretraining, a given percentage of tokens (usually 15%) is masked by:
+
+    * a special mask token with probability 0.8
+    * a random token different from the one masked with probability 0.1
+    * the same token with probability 0.1
+    
+- The model must predict the original sentence, but has a second objective: inputs are two sentences A and B (with a separation token in between). With probability 50%, the sentences are consecutive in the corpus, in the remaining 50% they are not related. The model has to predict if the sentences are consecutive or not.
+
+### Using Scaled Dot Product Attention (SDPA)
+
+PyTorch includes a native scaled dot-product attention (SDPA) operator as part of `torch.nn.functional`. This function 
+encompasses several implementations that can be applied depending on the inputs and the hardware in use. See the 
+[official documentation](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) 
+or the [GPU Inference](https://huggingface.co/docs/transformers/main/en/perf_infer_gpu_one#pytorch-scaled-dot-product-attention)
+page for more information.
+
+SDPA is used by default for `torch>=2.1.1` when an implementation is available, but you may also set 
+`attn_implementation="sdpa"` in `from_pretrained()` to explicitly request SDPA to be used.
+
+```
+from transformers import BertModel
+
+model = BertModel.from_pretrained("bert-base-uncased", torch_dtype=torch.float16, attn_implementation="sdpa")
+...
 ```
 
-</hfoption>
-<hfoption id="AutoModel">
+For the best speedups, we recommend loading the model in half-precision (e.g. `torch.float16` or `torch.bfloat16`).
 
-```py
-import torch
-from transformers import AutoModelForMaskedLM, AutoTokenizer
+On a local benchmark (A100-80GB, CPUx12, RAM 96.6GB, PyTorch 2.2.0, OS Ubuntu 22.04) with `float16`, we saw the 
+following speedups during training and inference.
 
-tokenizer = AutoTokenizer.from_pretrained(
-    "google-bert/bert-base-uncased",
-)
-model = AutoModelForMaskedLM.from_pretrained(
-    "google-bert/bert-base-uncased",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    attn_implementation="sdpa"
-)
-inputs = tokenizer("Plants create [MASK] through a process known as photosynthesis.", return_tensors="pt").to("cuda")
+#### Training
 
-with torch.no_grad():
-    outputs = model(**inputs)
-    predictions = outputs.logits
+|batch_size|seq_len|Time per batch (eager - s)|Time per batch (sdpa - s)|Speedup (%)|Eager peak mem (MB)|sdpa peak mem (MB)|Mem saving (%)|
+|----------|-------|--------------------------|-------------------------|-----------|-------------------|------------------|--------------|
+|4         |256    |0.023                     |0.017                    |35.472     |939.213            |764.834           |22.800        |
+|4         |512    |0.023                     |0.018                    |23.687     |1970.447           |1227.162          |60.569        |
+|8         |256    |0.023                     |0.018                    |23.491     |1594.295           |1226.114          |30.028        |
+|8         |512    |0.035                     |0.025                    |43.058     |3629.401           |2134.262          |70.054        |
+|16        |256    |0.030                     |0.024                    |25.583     |2874.426           |2134.262          |34.680        |
+|16        |512    |0.064                     |0.044                    |46.223     |6964.659           |3961.013          |75.830        |
 
-masked_index = torch.where(inputs['input_ids'] == tokenizer.mask_token_id)[1]
-predicted_token_id = predictions[0, masked_index].argmax(dim=-1)
-predicted_token = tokenizer.decode(predicted_token_id)
+#### Inference
 
-print(f"The predicted token is: {predicted_token}")
-```
+|batch_size|seq_len|Per token latency eager (ms)|Per token latency SDPA (ms)|Speedup (%)|Mem eager (MB)|Mem BT (MB)|Mem saved (%)|
+|----------|-------|----------------------------|---------------------------|-----------|--------------|-----------|-------------|
+|1         |128    |5.736                       |4.987                      |15.022     |282.661       |282.924    |-0.093       |
+|1         |256    |5.689                       |4.945                      |15.055     |298.686       |298.948    |-0.088       |
+|2         |128    |6.154                       |4.982                      |23.521     |314.523       |314.785    |-0.083       |
+|2         |256    |6.201                       |4.949                      |25.303     |347.546       |347.033    |0.148        |
+|4         |128    |6.049                       |4.987                      |21.305     |378.895       |379.301    |-0.107       |
+|4         |256    |6.285                       |5.364                      |17.166     |443.209       |444.382    |-0.264       |
 
-</hfoption>
-<hfoption id="transformers-cli">
 
-```bash
-echo -e "Plants create [MASK] through a process known as photosynthesis." | transformers-cli run --task fill-mask --model google-bert/bert-base-uncased --device 0
-```
 
-</hfoption>
-</hfoptions>
+## Resources
 
-## Notes
+A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with BERT. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
 
-- Inputs should be padded on the right because BERT uses absolute position embeddings.
+<PipelineTag pipeline="text-classification"/>
+
+- A blog post on [BERT Text Classification in a different language](https://www.philschmid.de/bert-text-classification-in-a-different-language).
+- A notebook for [Finetuning BERT (and friends) for multi-label text classification](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/BERT/Fine_tuning_BERT_(and_friends)_for_multi_label_text_classification.ipynb).
+- A notebook on how to [Finetune BERT for multi-label classification using PyTorch](https://colab.research.google.com/github/abhimishra91/transformers-tutorials/blob/master/transformers_multi_label_classification.ipynb). 🌎
+- A notebook on how to [warm-start an EncoderDecoder model with BERT for summarization](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/BERT2BERT_for_CNN_Dailymail.ipynb).
+- [`BertForSequenceClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification.ipynb).
+- [`TFBertForSequenceClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/text-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification-tf.ipynb).
+- [`FlaxBertForSequenceClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/text-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/text_classification_flax.ipynb).
+- [Text classification task guide](../tasks/sequence_classification)
+
+<PipelineTag pipeline="token-classification"/>
+
+- A blog post on how to use [Hugging Face Transformers with Keras: Fine-tune a non-English BERT for Named Entity Recognition](https://www.philschmid.de/huggingface-transformers-keras-tf).
+- A notebook for [Finetuning BERT for named-entity recognition](https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/BERT/Custom_Named_Entity_Recognition_with_BERT_only_first_wordpiece.ipynb) using only the first wordpiece of each word in the word label during tokenization. To propagate the label of the word to all wordpieces, see this [version](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/BERT/Custom_Named_Entity_Recognition_with_BERT.ipynb) of the notebook instead.
+- [`BertForTokenClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/token-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/token_classification.ipynb).
+- [`TFBertForTokenClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/token-classification) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/token_classification-tf.ipynb).
+- [`FlaxBertForTokenClassification`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/token-classification).
+- [Token classification](https://huggingface.co/course/chapter7/2?fw=pt) chapter of the 🤗 Hugging Face Course.
+- [Token classification task guide](../tasks/token_classification)
+
+<PipelineTag pipeline="fill-mask"/>
+
+- [`BertForMaskedLM`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/language-modeling#robertabertdistilbert-and-masked-language-modeling) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling.ipynb).
+- [`TFBertForMaskedLM`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/language-modeling#run_mlmpy) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/language_modeling-tf.ipynb).
+- [`FlaxBertForMaskedLM`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling#masked-language-modeling) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/masked_language_modeling_flax.ipynb).
+- [Masked language modeling](https://huggingface.co/course/chapter7/3?fw=pt) chapter of the 🤗 Hugging Face Course.
+- [Masked language modeling task guide](../tasks/masked_language_modeling)
+
+<PipelineTag pipeline="question-answering"/>
+
+- [`BertForQuestionAnswering`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/question-answering) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering.ipynb).
+- [`TFBertForQuestionAnswering`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/question-answering) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/question_answering-tf.ipynb).
+- [`FlaxBertForQuestionAnswering`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/flax/question-answering).
+- [Question answering](https://huggingface.co/course/chapter7/7?fw=pt) chapter of the 🤗 Hugging Face Course.
+- [Question answering task guide](../tasks/question_answering)
+
+**Multiple choice**
+- [`BertForMultipleChoice`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/multiple-choice) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multiple_choice.ipynb).
+- [`TFBertForMultipleChoice`] is supported by this [example script](https://github.com/huggingface/transformers/tree/main/examples/tensorflow/multiple-choice) and [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/multiple_choice-tf.ipynb).
+- [Multiple choice task guide](../tasks/multiple_choice)
+
+⚡️ **Inference**
+- A blog post on how to [Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia](https://huggingface.co/blog/bert-inferentia-sagemaker).
+- A blog post on how to [Accelerate BERT inference with DeepSpeed-Inference on GPUs](https://www.philschmid.de/bert-deepspeed-inference).
+
+⚙️ **Pretraining**
+- A blog post on [Pre-Training BERT with Hugging Face Transformers and Habana Gaudi](https://www.philschmid.de/pre-training-bert-habana).
+
+🚀 **Deploy**
+- A blog post on how to [Convert Transformers to ONNX with Hugging Face Optimum](https://www.philschmid.de/convert-transformers-to-onnx).
+- A blog post on how to [Setup Deep Learning environment for Hugging Face Transformers with Habana Gaudi on AWS](https://www.philschmid.de/getting-started-habana-gaudi#conclusion).
+- A blog post on [Autoscaling BERT with Hugging Face Transformers, Amazon SageMaker and Terraform module](https://www.philschmid.de/terraform-huggingface-amazon-sagemaker-advanced).
+- A blog post on [Serverless BERT with HuggingFace, AWS Lambda, and Docker](https://www.philschmid.de/serverless-bert-with-huggingface-aws-lambda-docker).
+- A blog post on [Hugging Face Transformers BERT fine-tuning using Amazon SageMaker and Training Compiler](https://www.philschmid.de/huggingface-amazon-sagemaker-training-compiler).
+- A blog post on [Task-specific knowledge distillation for BERT using Transformers & Amazon SageMaker](https://www.philschmid.de/knowledge-distillation-bert-transformers).
 
 ## BertConfig
 
@@ -107,10 +181,35 @@ echo -e "Plants create [MASK] through a process known as photosynthesis." | tran
     - create_token_type_ids_from_sequences
     - save_vocabulary
 
+<frameworkcontent>
+<pt>
+
 ## BertTokenizerFast
 
 [[autodoc]] BertTokenizerFast
 
+</pt>
+<tf>
+
+## TFBertTokenizer
+
+[[autodoc]] TFBertTokenizer
+
+</tf>
+</frameworkcontent>
+
+## Bert specific outputs
+
+[[autodoc]] models.bert.modeling_bert.BertForPreTrainingOutput
+
+[[autodoc]] models.bert.modeling_tf_bert.TFBertForPreTrainingOutput
+
+[[autodoc]] models.bert.modeling_flax_bert.FlaxBertForPreTrainingOutput
+
+
+<frameworkcontent>
+<pt>
+
 ## BertModel
 
 [[autodoc]] BertModel
@@ -156,9 +255,8 @@ echo -e "Plants create [MASK] through a process known as photosynthesis." | tran
 [[autodoc]] BertForQuestionAnswering
     - forward
 
-## TFBertTokenizer
-
-[[autodoc]] TFBertTokenizer
+</pt>
+<tf>
 
 ## TFBertModel
 
@@ -205,6 +303,9 @@ echo -e "Plants create [MASK] through a process known as photosynthesis." | tran
 [[autodoc]] TFBertForQuestionAnswering
     - call
 
+</tf>
+<jax>
+
 ## FlaxBertModel
 
 [[autodoc]] FlaxBertModel
@@ -250,10 +351,7 @@ echo -e "Plants create [MASK] through a process known as photosynthesis." | tran
 [[autodoc]] FlaxBertForQuestionAnswering
     - __call__
 
-## Bert specific outputs
+</jax>
+</frameworkcontent>
 
-[[autodoc]] models.bert.modeling_bert.BertForPreTrainingOutput
 
-[[autodoc]] models.bert.modeling_tf_bert.TFBertForPreTrainingOutput
-
-[[autodoc]] models.bert.modeling_flax_bert.FlaxBertForPreTrainingOutput

docs/source/en/model_doc/deit.md

@@ -19,7 +19,6 @@ rendered properly in your Markdown viewer.
 <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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white">
-<img alt="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/dinov2.md

@@ -16,7 +16,6 @@ specific language governing permissions and limitations under the License.
 <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">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/dinov2_with_registers.md

@@ -11,7 +11,6 @@ specific language governing permissions and limitations under the License.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/dpt.md

@@ -18,8 +18,6 @@ rendered properly in your Markdown viewer.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
-<img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 
 ## Overview

docs/source/en/model_doc/gemma3.md

@@ -15,63 +15,74 @@ 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="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
-    </div>
-</div>
+# Gemma3
 
-# Gemma 3
+## Overview
 
-[Gemma 3](https://goo.gle/Gemma3Report) is a multimodal model with pretrained and instruction-tuned variants, available in 1B, 13B, and 27B parameters. The architecture is mostly the same as the previous Gemma versions. The key differences are alternating 5 local sliding window self-attention layers for every global self-attention layer, support for a longer context length of 128K tokens, and a [SigLip](./siglip) encoder that can "pan & scan" high-resolution images to prevent information from disappearing in high resolution images or images with non-square aspect ratios.
+The Gemma 3 model was proposed in the [Gemma 3 Techncial Report](https://goo.gle/Gemma3Report) by Google. It is a vision-language model composed by a [SigLIP](siglip) vision encoder and a [Gemma 2](gemma_2) language decoder, linked by a multimodal linear projection. It cuts an image into a fixed number of tokens, in the same way as SigLIP, as long as the image does not exceed certain aspect ratio. For images that exceed the given aspect ratio, it crops the image into multiple smaller patches and concatenates them with the base image embedding. One particularity is that the model uses bidirectional attention on all the image tokens. In addition, the model interleaves sliding window local attention with full causal attention in the language backbone, where each sixth layer is a full causal attention layer.
 
-The instruction-tuned variant was post-trained with knowledge distillation and reinforcement learning.
+This model was contributed by [Ryan Mullins](https://huggingface.co/RyanMullins), [Raushan Turganbay](https://huggingface.co/RaushanTurganbay) [Arthur Zucker](https://huggingface.co/ArthurZ), and [Pedro Cuenca](https://huggingface.co/pcuenq).
 
-You can find all the original Gemma 3 checkpoints under the [Gemma 3](https://huggingface.co/collections/meta-llama/llama-2-family-661da1f90a9d678b6f55773b) release.
 
-> [!TIP]
-> Click on the Gemma 3 models in the right sidebar for more examples of how to apply Gemma to different vision and language tasks.
+## Usage tips
 
-The example below demonstrates how to generate text based on an image with [`Pipeline`] or the [`AutoModel`] class.
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+- For image+text and image-only inputs use `Gemma3ForConditionalGeneration`.
+- For text-only inputs use `Gemma3ForCausalLM` for generation to avoid loading the vision tower.
+- Each sample can contain multiple images, and the number of images can vary between samples. However, make sure to pass correctly batched images to the processor, where each batch is a list of one or more images.
+- The text passed to the processor should have a `<start_of_image>` token wherever an image should be inserted.
+- The processor has its own `apply_chat_template` method to convert chat messages to model inputs. See the examples below for more details on how to use it.
 
-```py
-import torch
-from transformers import pipeline
 
-pipeline = pipeline(
-    task="image-text-to-text",
-    model="google/gemma-3-4b-pt",
-    device=0,
-    torch_dtype=torch.bfloat16
-)
-pipeline(
-    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg",
-    text="<start_of_image> What is shown in this image?"
-)
+### Image cropping for high resolution images
+
+The model supports cropping images into smaller patches when the image aspect ratio exceeds a certain value. By default the images are not cropped and only the base image is forwarded to the model. Users can set `do_pan_and_scan=True` to obtain several crops per image along with the base image to improve the quality in DocVQA or similar tasks requiring higher resolution images.
+
+Pan and scan is an inference time optimization to handle images with skewed aspect ratios. When enabled, it improves performance on tasks related to document understanding, infographics, OCR, etc.
+
+```python
+
+processor = AutoProcessor.from_pretrained("google/gemma-3-4b-it", padding_side="left")
+
+url = "https://media.istockphoto.com/id/1192867753/photo/cow-in-berchida-beach-siniscola.jpg?s=612x612&w=0&k=20&c=v0hjjniwsMNfJSuKWZuIn8pssmD5h5bSN1peBd1CmH4="
+messages = [
+    {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "You are a helpful assistant."}
+        ]
+    },
+    {
+        "role": "user", "content": [
+            {"type": "image", "url": url},
+            {"type": "text", "text": "What is shown in this image?"},
+        ]
+    },
+]
+inputs = processor.apply_chat_template(
+    messages,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+    add_generation_prompt=True,
+    do_pan_and_scan=True,
+).to(model.device)
+
 ```
 
-</hfoption>
-<hfoption id="AutoModel">
 
-```py
-import torch
+## Usage Example
+
+### Single-image Inference
+
+```python
 from transformers import AutoProcessor, Gemma3ForConditionalGeneration
 
-model = Gemma3ForConditionalGeneration.from_pretrained(
-    "google/gemma-3-4b-it",
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    attn_implementation="sdpa"
-)
-processor = AutoProcessor.from_pretrained(
-    "google/gemma-3-4b-it",
-    padding_side="left"
-)
+model_id = "google/gemma-3-4b-it"
+model = Gemma3ForConditionalGeneration.from_pretrained(model_id, device_map="auto")
+processor = AutoProcessor.from_pretrained(model_id, padding_side="left")
 
+url = "https://media.istockphoto.com/id/1192867753/photo/cow-in-berchida-beach-siniscola.jpg?s=612x612&w=0&k=20&c=v0hjjniwsMNfJSuKWZuIn8pssmD5h5bSN1peBd1CmH4="
 messages = [
     {
         "role": "system",
@@ -81,7 +92,7 @@ messages = [
     },
     {
         "role": "user", "content": [
-            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
+            {"type": "image", "url": url},
             {"type": "text", "text": "What is shown in this image?"},
         ]
     },
@@ -92,43 +103,21 @@ inputs = processor.apply_chat_template(
     return_dict=True,
     return_tensors="pt",
     add_generation_prompt=True,
-).to("cuda")
+).to(model.device)
 
-output = model.generate(**inputs, max_new_tokens=50, cache_implementation="static")
-print(processor.decode(output[0], skip_special_tokens=True))
+output = model.generate(**inputs, max_new_tokens=50)
+print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])
 ```
 
-</hfoption>
-<hfoption id="transformers-cli">
+### Multi-image Inference
 
-```bash
-echo -e "Plants create energy through a process known as" | transformers-cli run --task text-generation --model google/gemma-3-1b-pt --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 [torchao](../quantization/torchao) to only quantize the weights to int4.
-
-```py
-# pip install torchao
-import torch
-from transformers import TorchAoConfig, Gemma3ForConditionalGeneration, AutoProcessor
-
-quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
-model = Gemma3ForConditionalGeneration.from_pretrained(
-    "google/gemma-3-27b-it",
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    quantization_config=quantization_config
-)
-processor = AutoProcessor.from_pretrained(
-    "google/gemma-3-27b-it",
-    padding_side="left"
-)
+```python
+model_id = "google/gemma-3-4b-it"
+model = Gemma3ForConditionalGeneration.from_pretrained(model_id, device_map="auto")
+processor = AutoProcessor.from_pretrained(model_id, padding_side="left")
 
+url_cow = "https://media.istockphoto.com/id/1192867753/photo/cow-in-berchida-beach-siniscola.jpg?s=612x612&w=0&k=20&c=v0hjjniwsMNfJSuKWZuIn8pssmD5h5bSN1peBd1CmH4="
+url_stop = "https://www.ilankelman.org/stopsigns/australia.jpg"
 messages = [
     {
         "role": "system",
@@ -138,8 +127,9 @@ messages = [
     },
     {
         "role": "user", "content": [
-            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
-            {"type": "text", "text": "What is shown in this image?"},
+            {"type": "image", "url": url_cow},
+            {"type": "image", "url": url_stop},
+            {"type": "text", "text": "Are these two images identical?"},
         ]
     },
 ]
@@ -149,81 +139,33 @@ inputs = processor.apply_chat_template(
     return_dict=True,
     return_tensors="pt",
     add_generation_prompt=True,
-).to("cuda")
+).to(model.device)
+
+output = model.generate(**inputs, max_new_tokens=50)
+print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])
 
-output = model.generate(**inputs, max_new_tokens=50, cache_implementation="static")
-print(processor.decode(output[0], skip_special_tokens=True))
 ```
 
-Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/blob/beb9b5b02246b9b7ee81ddf938f93f44cfeaad19/src/transformers/utils/attention_visualizer.py#L139) to better understand what tokens the model can and cannot attend to.
+### Text-only inference
 
-```py
-from transformers.utils.attention_visualizer import AttentionMaskVisualizer
+You can use the VLMs for text-only generation by omitting images in your input. However, you can also load the models in text-only mode as shown below. This will skip loading the vision tower and will save resources when you just need the LLM capabilities.
+```python
+from transformers import AutoTokenizer, Gemma3ForCausalLM
+
+model_id = "google/gemma-3-1b-it"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = Gemma3ForCausalLM.from_pretrained(model_id, device_map="auto")
+
+input_ids = tokenizer("Write me a poem about Machine Learning.", return_tensors="pt").to(model.device)
+
+outputs = model.generate(**input_ids, max_new_tokens=100)
+text = tokenizer.batch_decode(outputs, skip_special_tokens=True)
+
+print(text)
 
-visualizer = AttentionMaskVisualizer("google/gemma-3-4b-it")
-visualizer("<img>What is shown in this image?")
 ```
 
-## Notes
-
-- Use [`Gemma3ForConditionalGeneration`] for image-and-text and image-only inputs.
-- Gemma 3 supports multiple input images, but make sure the images are correctly batched before passing them to the processor. Each batch should be a list of one or more images.
-
-    ```py
-    url_cow = "https://media.istockphoto.com/id/1192867753/photo/cow-in-berchida-beach-siniscola.jpg?s=612x612&w=0&k=20&c=v0hjjniwsMNfJSuKWZuIn8pssmD5h5bSN1peBd1CmH4="
-    url_cat = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
-
-    messages =[
-        {
-            "role": "system",
-            "content": [
-                {"type": "text", "text": "You are a helpful assistant."}
-            ]
-        },
-        {
-            "role": "user",
-            "content": [
-                {"type": "image", "url": url_cow},
-                {"type": "image", "url": url_cat},
-                {"type": "text", "text": "Which image is cuter?"},
-            ]
-        },
-    ]
-    ```
-- Text passed to the processor should have a `<start_of_image>` token wherever an image should be inserted.
-- The processor has its own [`~ProcessorMixin.apply_chat_template`] method to convert chat messages to model inputs.
-- By default, images aren't cropped and only the base image is forwarded to the model. In high resolution images or images with non-square aspect ratios, artifacts can result because the vision encoder uses a fixed resolution of 896x896. To prevent these artifacts and improve performance during inference, set `do_pan_and_scan=True` to crop the image into multiple smaller patches and concatenate them with the base image embedding. You can disable pan and scan for faster inference.
-
-    ```diff
-    inputs = processor.apply_chat_template(
-        messages,
-        tokenize=True,
-        return_dict=True,
-        return_tensors="pt",
-        add_generation_prompt=True,
-    +   do_pan_and_scan=True,
-        ).to("cuda")
-    ```
-- For Gemma-3 1B checkpoint trained in text-only mode, use [`AutoModelForCausalLM`] instead.
-
-    ```py
-    import torch
-    from transformers import AutoModelForCausalLM, AutoTokenizer
-
-    tokenizer = AutoTokenizer.from_pretrained(
-        "google/gemma-3-1b-pt",
-    )
-    model = AutoModelForCausalLM.from_pretrained(
-        "google/gemma-3-1b-pt",
-        torch_dtype=torch.bfloat16,
-        device_map="auto",
-        attn_implementation="sdpa"
-    )
-    input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to("cuda")
-
-    output = model.generate(**input_ids, cache_implementation="static")
-    print(tokenizer.decode(output[0], skip_special_tokens=True))
-    ```
 
 ## Gemma3ImageProcessor
 

docs/source/en/model_doc/hubert.md

@@ -71,10 +71,9 @@ pip install -U flash-attn --no-build-isolation
 Below is an expected speedup diagram comparing the pure inference time between the native implementation in transformers of `facebook/hubert-large-ls960-ft`, the flash-attention-2 and the sdpa (scale-dot-product-attention) version. We show the average speedup obtained on the `librispeech_asr` `clean` validation split: 
 
 ```python
->>> from transformers import HubertModel
->>> import torch
+>>> from transformers import Wav2Vec2Model
 
->>> model = HubertModel.from_pretrained("facebook/hubert-large-ls960-ft", torch_dtype=torch.float16, attn_implementation="flash_attention_2").to("cuda")
+model = Wav2Vec2Model.from_pretrained("facebook/hubert-large-ls960-ft", torch_dtype=torch.float16, attn_implementation="flash_attention_2").to(device)
 ...
 ```
 

docs/source/en/model_doc/ijepa.md

@@ -18,7 +18,6 @@ rendered properly in your Markdown viewer.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/llama.md

@@ -14,111 +14,79 @@ 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">
-        <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
-    </div>
+# LLaMA
+
+<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">
+<img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 
-# Llama
+## Overview
 
-[Llama](https://huggingface.co/papers/2302.13971) is a family of large language models ranging from 7B to 65B parameters. These models are focused on efficient inference (important for serving language models) by training a smaller model on more tokens rather than training a larger model on fewer tokens. The Llama model is based on the GPT architecture, but it uses pre-normalization to improve training stability, replaces ReLU with SwiGLU to improve performance, and replaces absolute positional embeddings with rotary positional embeddings (RoPE) to better handle longer sequence lengths.
+The LLaMA model was proposed in [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971) by Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, Guillaume Lample. It is a collection of foundation language models ranging from 7B to 65B parameters.
 
-You can find all the original Llama checkpoints under the [Huggy Llama](https://huggingface.co/huggyllama) organization.
+The abstract from the paper is the following:
 
-> [!TIP]
-> Click on the Llama models in the right sidebar for more examples of how to apply Llama to different language tasks.
+*We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community. *
 
-The example below demonstrates how to generate text with [`Pipeline`] or the [`AutoModel`], and from the command line.
+This model was contributed by [zphang](https://huggingface.co/zphang) with contributions from [BlackSamorez](https://huggingface.co/BlackSamorez). The code of the implementation in Hugging Face is based on GPT-NeoX [here](https://github.com/EleutherAI/gpt-neox). The original code of the authors can be found [here](https://github.com/facebookresearch/llama).
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+## Usage tips
 
-```py
-import torch
-from transformers import pipeline
-
-pipeline = pipeline(
-    task="text-generation",
-    model="huggyllama/llama-7b",
-    torch_dtype=torch.float16,
-    device=0
-)
-pipeline("Plants create energy through a process known as")
-```
-
-</hfoption>
-<hfoption id="AutoModel">
-
-```py
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-tokenizer = AutoTokenizer.from_pretrained(
-    "huggyllama/llama-7b",
-)
-model = AutoModelForCausalLM.from_pretrained(
-    "huggyllama/llama-7b",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    attn_implementation="sdpa"
-)
-input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to("cuda")
-
-output = model.generate(**input_ids, cache_implementation="static")
-print(tokenizer.decode(output[0], skip_special_tokens=True))
-```
-
-</hfoption>
-<hfoption id="transformers-cli">
+- Weights for the LLaMA models can be obtained from by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form)
+- After downloading the weights, they will need to be converted to the Hugging Face Transformers format using the [conversion script](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py). The script can be called with the following (example) command:
 
 ```bash
-echo -e "Plants create energy through a process known as" | transformers-cli run --task text-generation --model huggyllama/llama-7b --device 0
+python src/transformers/models/llama/convert_llama_weights_to_hf.py \
+    --input_dir /path/to/downloaded/llama/weights --model_size 7B --output_dir /output/path
 ```
 
-</hfoption>
-</hfoptions>
+- After conversion, the model and tokenizer can be loaded via:
 
-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.
+```python
+from transformers import LlamaForCausalLM, LlamaTokenizer
 
-The example below uses [torchao](../quantization/torchao) to only quantize the weights to int4.
-
-```py
-# pip install torchao
-import torch
-from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
-
-quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
-model = AutoModelForCausalLM.from_pretrained(
-    "huggyllama/llama-30b",
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    quantization_config=quantization_config
-)
-
-tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-30b")
-input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to("cuda")
-
-output = model.generate(**input_ids, cache_implementation="static")
-print(tokenizer.decode(output[0], skip_special_tokens=True))
+tokenizer = LlamaTokenizer.from_pretrained("/output/path")
+model = LlamaForCausalLM.from_pretrained("/output/path")
 ```
 
-Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/blob/beb9b5b02246b9b7ee81ddf938f93f44cfeaad19/src/transformers/utils/attention_visualizer.py#L139) to better understand what tokens the model can and cannot attend to.
+Note that executing the script requires enough CPU RAM to host the whole model in float16 precision (even if the biggest versions
+come in several checkpoints they each contain a part of each weight of the model, so we need to load them all in RAM). For the 65B model, it's thus 130GB of RAM needed.
 
-```py
-from transformers.utils.attention_visualizer import AttentionMaskVisualizer
+- The LLaMA tokenizer is a BPE model based on [sentencepiece](https://github.com/google/sentencepiece). One quirk of sentencepiece is that when decoding a sequence, if the first token is the start of the word (e.g. "Banana"), the tokenizer does not prepend the prefix space to the string.
 
-visualizer = AttentionMaskVisualizer("huggyllama/llama-7b")
-visualizer("Plants create energy through a process known as")
-```
+This model was contributed by [zphang](https://huggingface.co/zphang) with contributions from [BlackSamorez](https://huggingface.co/BlackSamorez). The code of the implementation in Hugging Face is based on GPT-NeoX [here](https://github.com/EleutherAI/gpt-neox). The original code of the authors can be found [here](https://github.com/facebookresearch/llama). The Flax version of the implementation was contributed by [afmck](https://huggingface.co/afmck) with the code in the implementation based on Hugging Face's Flax GPT-Neo.
 
-## Notes
 
-- The tokenizer is a byte-pair encoding model based on [SentencePiece](https://github.com/google/sentencepiece). During decoding, if the first token is the start of the word (for example, "Banana"), the tokenizer doesn't prepend the prefix space to the string.
+Based on the original LLaMA model, Meta AI has released some follow-up works:
+
+- **Llama2**: Llama2 is an improved version of Llama with some architectural tweaks (Grouped Query Attention), and is pre-trained on 2Trillion tokens. Refer to the documentation of Llama2 which can be found [here](llama2).
+
+## Resources
+
+A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with LLaMA. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
+
+<PipelineTag pipeline="text-classification"/>
+
+- A [notebook](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-sst2.ipynb#scrollTo=f04ba4d2) on how to use prompt tuning to adapt the LLaMA model for text classification task. 🌎
+
+<PipelineTag pipeline="question-answering"/>
+
+- [StackLLaMA: A hands-on guide to train LLaMA with RLHF](https://huggingface.co/blog/stackllama#stackllama-a-hands-on-guide-to-train-llama-with-rlhf), a blog post about how to train LLaMA to answer questions on [Stack Exchange](https://stackexchange.com/) with RLHF.
+
+⚗️ Optimization
+- A [notebook](https://colab.research.google.com/drive/1SQUXq1AMZPSLD4mk3A3swUIc6Y2dclme?usp=sharing) on how to fine-tune LLaMA model using xturing library on GPU which has limited memory. 🌎 
+
+⚡️ Inference
+- A [notebook](https://colab.research.google.com/github/DominguesM/alpaca-lora-ptbr-7b/blob/main/notebooks/02%20-%20Evaluate.ipynb) on how to run the LLaMA Model using PeftModel from the 🤗 PEFT library. 🌎 
+- A [notebook](https://colab.research.google.com/drive/1l2GiSSPbajVyp2Nk3CFT4t3uH6-5TiBe?usp=sharing) on how to load a PEFT adapter LLaMA model with LangChain. 🌎
+
+🚀 Deploy
+- A [notebook](https://colab.research.google.com/github/lxe/simple-llama-finetuner/blob/master/Simple_LLaMA_FineTuner.ipynb#scrollTo=3PM_DilAZD8T) on how to fine-tune LLaMA model using LoRA method via the 🤗 PEFT library with intuitive UI. 🌎 
+- A [notebook](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart-foundation-models/text-generation-open-llama.ipynb) on how to deploy Open-LLaMA model for text generation on Amazon SageMaker. 🌎 
 
 ## LlamaConfig
 

docs/source/en/model_doc/llama2.md

@@ -14,125 +14,97 @@ 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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
-        ">
-    </div>
+# Llama2
+
+<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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
+">
 </div>
 
-# Llama 2
+## Overview
 
-[Llama 2](https://huggingface.co/papers/2307.09288) is a family of large language models, Llama 2 and Llama 2-Chat, available in 7B, 13B, and 70B parameters. The Llama 2 model mostly keeps the same architecture as [Llama](./llama), but it is pretrained on more tokens, doubles the context length, and uses grouped-query attention (GQA) in the 70B model to improve inference.
+The Llama2 model was proposed in [LLaMA: Open Foundation and Fine-Tuned Chat Models](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/) by Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushka rMishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing EllenTan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom. It is a collection of foundation language models ranging from 7B to 70B parameters, with checkpoints finetuned for chat application!
 
-Llama 2-Chat is trained with supervised fine-tuning (SFT), and reinforcement learning with human feedback (RLHF) - rejection sampling and proximal policy optimization (PPO) - is applied to the fine-tuned model to align the chat model with human preferences.
+The abstract from the paper is the following:
 
-You can find all the original Llama 2 checkpoints under the [Llama 2 Family](https://huggingface.co/collections/meta-llama/llama-2-family-661da1f90a9d678b6f55773b) collection.
+*In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.*
 
-> [!TIP]
-> Click on the Llama 2 models in the right sidebar for more examples of how to apply Llama to different language tasks.
+Checkout all Llama2 model checkpoints [here](https://huggingface.co/models?search=llama2).
+This model was contributed by [Arthur Zucker](https://huggingface.co/ArthurZ) with contributions from [Lysandre Debut](https://huggingface.co/lysandre). The code of the implementation in Hugging Face is based on GPT-NeoX [here](https://github.com/EleutherAI/gpt-neox). The original code of the authors can be found [here](https://github.com/facebookresearch/llama).
 
-The example below demonstrates how to generate text with [`Pipeline`], [`AutoModel`], and how to chat with Llama 2-Chat from the command line.
+## Usage tips
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+<Tip warning={true}>
 
-```py
-import torch
-from transformers import pipeline
+The `Llama2` models were trained using `bfloat16`, but the original inference uses `float16`. The checkpoints uploaded on the Hub use `torch_dtype = 'float16'`, which will be
+used by the `AutoModel` API to cast the checkpoints from `torch.float32` to `torch.float16`. 
 
-pipeline = pipeline(
-    task="text-generation",
-    model="meta-llama/Llama-2-7b-hf",
-    torch_dtype=torch.float16,
-    device=0
-)
-pipeline("Plants create energy through a process known as")
-```
+The `dtype` of the online weights is mostly irrelevant unless you are using `torch_dtype="auto"` when initializing a model using `model = AutoModelForCausalLM.from_pretrained("path", torch_dtype = "auto")`. The reason is that the model will first be downloaded ( using the `dtype` of the checkpoints online), then it will be casted to the default `dtype` of `torch` (becomes `torch.float32`), and finally, if there is a `torch_dtype` provided in the config, it will be used. 
 
-</hfoption>
-<hfoption id="AutoModel">
+Training the model in `float16` is not recommended and is known to produce `nan`; as such, the model should be trained in `bfloat16`.
 
-```py
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+</Tip>
 
-tokenizer = AutoTokenizer.from_pretrained(
-    "meta-llama/Llama-2-7b-hf",
-)
-model = AutoModelForCausalLM.from_pretrained(
-    "meta-llama/Llama-2-7b-hf",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    attn_implementation="sdpa"
-)
-input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to("cuda")
+Tips:
 
-output = model.generate(**input_ids, cache_implementation="static")
-print(tokenizer.decode(output[0], skip_special_tokens=True))
-```
-
-</hfoption>
-<hfoption id="transformers-cli">
+- Weights for the Llama2 models can be obtained by filling out [this form](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
+- The architecture is very similar to the first Llama, with the addition of Grouped Query Attention (GQA) following this [paper](https://arxiv.org/pdf/2305.13245.pdf)
+- Setting `config.pretraining_tp` to a value different than 1 will activate the more accurate but slower computation of the linear layers, which should better match the original logits.
+- The original model uses `pad_id = -1` which means that there is no padding token. We can't have the same logic, make sure to add a padding token using `tokenizer.add_special_tokens({"pad_token":"<pad>"})` and resize the token embedding accordingly. You should also set the `model.config.pad_token_id`. The `embed_tokens` layer of the model is initialized with `self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.config.padding_idx)`, which makes sure that encoding the padding token will output zeros, so passing it when initializing is recommended.
+- After filling out the form and gaining access to the model checkpoints, you should be able to use the already converted checkpoints. Otherwise, if you are converting your own model, feel free to use the [conversion script](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py). The script can be called with the following (example) command:
 
 ```bash
-transformers-cli chat --model_name_or_path meta-llama/Llama-2-7b-chat-hf --torch_dtype auto --attn_implementation flash_attention_2
+python src/transformers/models/llama/convert_llama_weights_to_hf.py \
+    --input_dir /path/to/downloaded/llama/weights --model_size 7B --output_dir /output/path
 ```
 
-</hfoption>
-</hfoptions>
+- After conversion, the model and tokenizer can be loaded via:
 
-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.
+```python
+from transformers import LlamaForCausalLM, LlamaTokenizer
 
-The example below uses [torchao](../quantization/torchao) to only quantize the weights to int4.
-
-```py
-# pip install torchao
-import torch
-from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
-
-quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
-model = AutoModelForCausalLM.from_pretrained(
-    "meta-llama/Llama-2-13b-hf",
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    quantization_config=quantization_config
-)
-
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-13b-hf")
-input_ids = tokenizer("Plants create energy through a process known as", return_tensors="pt").to("cuda")
-
-output = model.generate(**input_ids, cache_implementation="static")
-print(tokenizer.decode(output[0], skip_special_tokens=True))
+tokenizer = LlamaTokenizer.from_pretrained("/output/path")
+model = LlamaForCausalLM.from_pretrained("/output/path")
 ```
 
-Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/blob/beb9b5b02246b9b7ee81ddf938f93f44cfeaad19/src/transformers/utils/attention_visualizer.py#L139) to better understand what tokens the model can and cannot attend to.
+Note that executing the script requires enough CPU RAM to host the whole model in float16 precision (even if the biggest versions
+come in several checkpoints they each contain a part of each weight of the model, so we need to load them all in RAM). For the 75B model, it's thus 145GB of RAM needed.
 
-```py
-from transformers.utils.attention_visualizer import AttentionMaskVisualizer
+- The LLaMA tokenizer is a BPE model based on [sentencepiece](https://github.com/google/sentencepiece). One quirk of sentencepiece is that when decoding a sequence, if the first token is the start of the word (e.g. "Banana"), the tokenizer does not prepend the prefix space to the string.
 
-visualizer = AttentionMaskVisualizer("meta-llama/Llama-2-7b-hf")
-visualizer("Plants create energy through a process known as")
-```
+- When using Flash Attention 2 via `attn_implementation="flash_attention_2"`, don't pass `torch_dtype` to the `from_pretrained` class method and use Automatic Mixed-Precision training. When using `Trainer`, it is simply specifying either `fp16` or `bf16` to `True`. Otherwise, make sure you are using `torch.autocast`. This is required because the Flash Attention only support `fp16` and `bf16` data type.
 
-## Notes
 
-- Setting `config.pretraining_tp` to a value besides `1` activates a more accurate but slower computation of the linear layers. This matches the original logits better.
-- The original model uses `pad_id = -1` to indicate a padding token. The Transformers implementation requires adding a padding token and resizing the token embedding accordingly.
+## Resources
 
-    ```py
-    tokenizer.add_special_tokens({"pad_token":"<pad>"})
-    # update model config with padding token
-    model.config.pad_token_id
-    ```
-- It is recommended to initialize the `embed_tokens` layer with the following code to ensure encoding the padding token outputs zeros.
+A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with LLaMA2. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
+
+- [Llama 2 is here - get it on Hugging Face](https://huggingface.co/blog/llama2), a blog post about Llama 2 and how to use it with 🤗 Transformers and 🤗 PEFT.
+- [LLaMA 2 - Every Resource you need](https://www.philschmid.de/llama-2), a compilation of relevant resources to learn about LLaMA 2 and how to get started quickly.
+
+<PipelineTag pipeline="text-generation"/>
+
+- A [notebook](https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing) on how to fine-tune Llama 2 in Google Colab using QLoRA and 4-bit precision. 🌎
+- A [notebook](https://colab.research.google.com/drive/134o_cXcMe_lsvl15ZE_4Y75Kstepsntu?usp=sharing) on how to fine-tune the "Llama-v2-7b-guanaco" model with 4-bit QLoRA and generate Q&A datasets from PDFs. 🌎
+
+<PipelineTag pipeline="text-classification"/>
+
+- A [notebook](https://colab.research.google.com/drive/1ggaa2oRFphdBmqIjSEbnb_HGkcIRC2ZB?usp=sharing) on how to fine-tune the Llama 2 model with QLoRa, TRL, and Korean text classification dataset. 🌎🇰🇷
+
+⚗️ Optimization
+- [Fine-tune Llama 2 with DPO](https://huggingface.co/blog/dpo-trl), a guide to using the TRL library's DPO method to fine tune Llama 2 on a specific dataset.
+- [Extended Guide: Instruction-tune Llama 2](https://www.philschmid.de/instruction-tune-llama-2), a guide to training Llama 2 to generate instructions from inputs, transforming the model from instruction-following to instruction-giving.
+- A [notebook](https://colab.research.google.com/drive/1SYpgFpcmtIUzdE7pxqknrM4ArCASfkFQ?usp=sharing) on how to fine-tune the Llama 2 model on a personal computer using QLoRa and TRL. 🌎
+
+⚡️ Inference
+- A [notebook](https://colab.research.google.com/drive/1TC56ArKerXUpbgRy5vM3woRsbTEVNq7h?usp=sharing) on how to quantize the Llama 2 model using GPTQ from the AutoGPTQ library. 🌎
+- A [notebook](https://colab.research.google.com/drive/1X1z9Q6domMKl2CnEM0QGHNwidLfR4dW2?usp=sharing) on how to run the Llama 2 Chat Model with 4-bit quantization on a local computer or Google Colab. 🌎
+
+🚀 Deploy
+- [Fine-tune LLaMA 2 (7-70B) on Amazon SageMaker](https://www.philschmid.de/sagemaker-llama2-qlora), a complete guide from setup to QLoRA fine-tuning and deployment on Amazon SageMaker.
+- [Deploy Llama 2 7B/13B/70B on Amazon SageMaker](https://www.philschmid.de/sagemaker-llama-llm), a guide on using Hugging Face's LLM DLC container for secure and scalable deployment.
 
-    ```py
-    self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.config.padding_idx)
-    ```
-- The tokenizer is a byte-pair encoding model based on [SentencePiece](https://github.com/google/sentencepiece). During decoding, if the first token is the start of the word (for example, "Banana"), the tokenizer doesn't prepend the prefix space to the string.
-- Don't use the `torch_dtype` parameter in [`~AutoModel.from_pretrained`] if you're using FlashAttention-2 because it only supports fp16 or bf16. You should use [Automatic Mixed Precision](https://pytorch.org/tutorials/recipes/recipes/amp_recipe.html), set fp16 or bf16 to `True` if using [`Trainer`], or use [torch.autocast](https://pytorch.org/docs/stable/amp.html#torch.autocast).
 
 ## LlamaConfig
 

docs/source/en/model_doc/mistral3.md

@@ -1,234 +0,0 @@
-<!--Copyright 2025 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.
-
--->
-
-# Mistral3
-
-## Overview
-
-Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.
-
-It is ideal for:
-- Fast-response conversational agents.
-- Low-latency function calling.
-- Subject matter experts via fine-tuning.
-- Local inference for hobbyists and organizations handling sensitive data.
-- Programming and math reasoning.
-- Long document understanding.
-- Visual understanding.
-
-This model was contributed by [cyrilvallez](https://huggingface.co/cyrilvallez) and [yonigozlan](https://huggingface.co/yonigozlan).
-
-The original code can be found [here](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/pixtral.py) and [here](https://github.com/mistralai/mistral-common).
-
-## Usage example
-
-### Inference with Pipeline
-
-Here is how you can use the `image-text-to-text` pipeline to perform inference with the `Mistral3` models in just a few lines of code:
-```python
->>> from transformers import pipeline
-
->>> messages = [
-...     {
-...         "role": "user",
-...         "content": [
-...             {
-...                 "type": "image",
-...                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg",
-...             },
-...             {"type": "text", "text": "Describe this image."},
-...         ],
-...     },
-... ]
-
->>> pipe = pipeline("image-text-to-text", model="mistralai/Mistral-Small-3.1-24B-Instruct-2503", torch_dtype=torch.bfloat16)
->>> outputs = pipe(text=messages, max_new_tokens=50, return_full_text=False)
->>> outputs[0]["generated_text"]
-'The image depicts a vibrant and lush garden scene featuring a variety of wildflowers and plants. The central focus is on a large, pinkish-purple flower, likely a Greater Celandine (Chelidonium majus), with a'
-```
-### Inference on a single image
-
-This example demonstrates how to perform inference on a single image with the Mistral3 models using chat templates.
-
-```python
->>> from transformers import AutoProcessor, AutoModelForImageTextToText
->>> import torch
-
->>> torch_device = "cuda"
->>> model_checkpoint = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
->>> processor = AutoProcessor.from_pretrained(model_checkpoint)
->>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)
-
->>> messages = [
-...     {
-...         "role": "user",
-...         "content": [
-...             {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
-...             {"type": "text", "text": "Describe this image"},
-...         ],
-...     }
-... ]
-
->>> inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
-
->>> generate_ids = model.generate(**inputs, max_new_tokens=20)
->>> decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
-
->>> decoded_output
-"The image depicts two cats lying on a pink blanket. The larger cat, which appears to be an"...
-```
-
-### Text-only generation
-This example shows how to generate text using the Mistral3 model without providing any image input.
-
-
-````python
->>> from transformers import AutoProcessor, AutoModelForImageTextToText
->>> import torch
-
->>> torch_device = "cuda"
->>> model_checkpoint = ".mistralai/Mistral-Small-3.1-24B-Instruct-2503"
->>> processor = AutoProcessor.from_pretrained(model_checkpoint)
->>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)
-
->>> SYSTEM_PROMPT = "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat."
->>> user_prompt = "Give me 5 non-formal ways to say 'See you later' in French."
-
->>> messages = [
-...    {"role": "system", "content": SYSTEM_PROMPT},
-...    {"role": "user", "content": user_prompt},
-... ]
-
->>> text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
->>> inputs = processor(text=text, return_tensors="pt").to(0, dtype=torch.float16)
->>> generate_ids = model.generate(**inputs, max_new_tokens=50, do_sample=False)
->>> decoded_output = processor.batch_decode(generate_ids[:, inputs["input_ids"].shape[1] :], skip_special_tokens=True)[0]
-
->>> print(decoded_output)
-"1. À plus tard!
-2. Salut, à plus!
-3. À toute!
-4. À la prochaine!
-5. Je me casse, à plus!
-
-```
- /\_/\
-( o.o )
- > ^ <
-```"
-````
-
-### Batched image and text inputs
-Mistral3 models also support batched image and text inputs.
-
-```python
->>> from transformers import AutoProcessor, AutoModelForImageTextToText
->>> import torch
-
->>> torch_device = "cuda"
->>> model_checkpoint = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
->>> processor = AutoProcessor.from_pretrained(model_checkpoint)
->>> model = AutoModelForImageTextToText.from_pretrained(model_checkpoint, device_map=torch_device, torch_dtype=torch.bfloat16)
-
->>> messages = [
-...     [
-...         {
-...             "role": "user",
-...             "content": [
-...                 {"type": "image", "url": "https://llava-vl.github.io/static/images/view.jpg"},
-...                 {"type": "text", "text": "Write a haiku for this image"},
-...             ],
-...         },
-...     ],
-...     [
-...         {
-...             "role": "user",
-...             "content": [
-...                 {"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"},
-...                 {"type": "text", "text": "Describe this image"},
-...             ],
-...         },
-...     ],
-... ]
-
-
->>> inputs = processor.apply_chat_template(messages, padding=True, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
-
->>> output = model.generate(**inputs, max_new_tokens=25)
-
->>> decoded_outputs = processor.batch_decode(output, skip_special_tokens=True)
->>> decoded_outputs
-["Write a haiku for this imageCalm waters reflect\nWhispers of the forest's breath\nPeace on wooden path"
-, "Describe this imageThe image depicts a vibrant street scene in what appears to be a Chinatown district. The focal point is a traditional Chinese"]
-```
-
-### Batched multi-image input and quantization with BitsAndBytes
-This implementation of the Mistral3 models supports batched text-images inputs with different number of images for each text.
-This example also how to use `BitsAndBytes` to load the model in 4bit quantization.
-
-```python
->>> from transformers import AutoProcessor, AutoModelForImageTextToText, BitsAndBytesConfig
->>> import torch
-
->>> torch_device = "cuda"
->>> model_checkpoint = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
->>> processor = AutoProcessor.from_pretrained(model_checkpoint)
->>> quantization_config = BitsAndBytesConfig(load_in_4bit=True)
->>> model = AutoModelForImageTextToText.from_pretrained(
-...     model_checkpoint, quantization_config=quantization_config
-... )
-
->>> messages = [
-...     [
-...         {
-...             "role": "user",
-...             "content": [
-...                 {"type": "image", "url": "https://llava-vl.github.io/static/images/view.jpg"},
-...                 {"type": "text", "text": "Write a haiku for this image"},
-...             ],
-...         },
-...     ],
-...     [
-...         {
-...             "role": "user",
-...             "content": [
-...                 {"type": "image", "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"},
-...                 {"type": "image", "url": "https://thumbs.dreamstime.com/b/golden-gate-bridge-san-francisco-purple-flowers-california-echium-candicans-36805947.jpg"},
-...                 {"type": "text", "text": "These images depict two different landmarks. Can you identify them?"},
-...             ],
-...         },
-...     ],
->>> ]
-
->>> inputs = processor.apply_chat_template(messages, padding=True, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
-
->>> output = model.generate(**inputs, max_new_tokens=25)
-
->>> decoded_outputs = processor.batch_decode(output, skip_special_tokens=True)
->>> decoded_outputs
-["Write a haiku for this imageSure, here is a haiku inspired by the image:\n\nCalm lake's wooden path\nSilent forest stands guard\n", "These images depict two different landmarks. Can you identify them? Certainly! The images depict two iconic landmarks:\n\n1. The first image shows the Statue of Liberty in New York City."]
-```
-
-
-## Mistral3Config
-
-[[autodoc]] Mistral3Config
-
-
-## Mistral3ForConditionalGeneration
-
-[[autodoc]] Mistral3ForConditionalGeneration
-    - forward

docs/source/en/model_doc/paligemma.md

@@ -14,153 +14,89 @@ 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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
-        <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
-    </div>
-</div>
-
 # PaliGemma
 
-[PaliGemma](https://huggingface.co/papers/2407.07726) is a family of vision-language models (VLMs), combining [SigLIP](./siglip) with the [Gemma](./gemma) 2B model. PaliGemma is available in 3B, 10B, and 28B parameters. The main purpose of PaliGemma is to provide an adaptable base VLM that is easy to transfer to other tasks. The SigLIP vision encoder is a "shape optimized" contrastively pretrained [ViT](./vit) that converts an image into a sequence of tokens and prepended to an optional prompt. The Gemma 2B model is used as the decoder. PaliGemma uses full attention on all image and text tokens to maximize its capacity.
+<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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
+<img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
+</div>
 
-[PaliGemma 2](https://huggingface.co/papers/2412.03555) improves on the first model by using Gemma 2 (2B, 9B, and 27B parameter variants) as the decoder. These are available as **pt** or **mix** variants. The **pt** checkpoints are intended for further fine-tuning and the **mix** checkpoints are ready for use out of the box.
+## Overview
 
-You can find all the original PaliGemma checkpoints under the [PaliGemma](https://huggingface.co/collections/google/paligemma-release-6643a9ffbf57de2ae0448dda), [PaliGemma 2](https://huggingface.co/collections/google/paligemma-2-release-67500e1e1dbfdd4dee27ba48), and [PaliGemma 2 Mix](https://huggingface.co/collections/google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4) collections.
+The PaliGemma model was proposed in [PaliGemma – Google's Cutting-Edge Open Vision Language Model](https://huggingface.co/blog/paligemma) by Google. It is a 3B vision-language model composed by a [SigLIP](siglip) vision encoder and a [Gemma](gemma) language decoder linked by a multimodal linear projection. It cuts an image into a fixed number of VIT tokens and prepends it to an optional prompt. One particularity is that the model uses full block attention on all the image tokens plus the input text tokens. It comes in 3 resolutions, 224x224, 448x448 and 896x896 with 3 base models, with 55 fine-tuned versions for different tasks, and 2 mix models.
 
-> [!TIP]
-> Click on the PaliGemma models in the right sidebar for more examples of how to apply PaliGemma to different vision and language tasks.
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/paligemma/paligemma_arch.png"
+alt="drawing" width="600"/>
 
-The example below demonstrates how to generate text based on an image with [`Pipeline`] or the [`AutoModel`] class.
+<small> PaliGemma architecture. Taken from the <a href="https://huggingface.co/blog/paligemma">blog post.</a> </small>
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+This model was contributed by [Molbap](https://huggingface.co/Molbap).
 
-```py
-import torch
-from transformers import pipeline
+## Usage tips
 
-pipeline = pipeline(
-    task="image-text-to-text",
-    model="google/paligemma2-3b-mix-224",
-    device=0,
-    torch_dtype=torch.bfloat16
-)
-pipeline(
-    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg",
-    text="What is in this image?"
-)
+- PaliGemma is not meant for conversational use, and it works best when fine-tuning to a specific use case. Some downstream tasks on which PaliGemma can be fine-tuned include image captioning, visual question answering (VQA), object detection, referring expression segmentation and document understanding.
+- One can use `PaliGemmaProcessor` to prepare images, text and optional labels for the model. When fine-tuning a PaliGemma model, the `suffix` argument can be passed to the processor which creates the `labels` for the model:
+
+```python
+prompt = "What is on the flower?"
+answer = "a bee"
+inputs = processor(images=raw_image, text=prompt, suffix=answer, return_tensors="pt")
 ```
 
-</hfoption>
-<hfoption id="AutoModel">
+## Usage Example
 
-```py
-import torch
-import requests
-from PIL import Image
+The model can accept a single or multiple images. According to the [paper](https://arxiv.org/abs/2407.07726v1), the checkpoint PaliGemma can transfer to tasks which take multiple images as input. NLVR2 is one such task, which asks one question about two images, and requires looking at both to give the correct answer. Here's an example code for single and multi image inference.
+
+### Single-image Inference
+
+```python
 from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
 
-model = PaliGemmaForConditionalGeneration.from_pretrained(
-    "google/paligemma2-3b-mix-224",
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    attn_implementation="sdpa"
-)
-processor = AutoProcessor.from_pretrained(
-    "google/paligemma2-3b-mix-224",
-)
+model_id = "google/paligemma-3b-mix-224"
+model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id)
 
-prompt = "What is in this image?"
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
-image = Image.open(requests.get(url, stream=True).raw)
-inputs = processor(image, prompt, return_tensors="pt").to("cuda")
+prompt = "What is on the flower?"
+image_file = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg?download=true"
+raw_image = Image.open(requests.get(image_file, stream=True).raw)
+inputs = processor(raw_image, prompt, return_tensors="pt")
+output = model.generate(**inputs, max_new_tokens=20)
 
-output = model.generate(**inputs, max_new_tokens=50, cache_implementation="static")
-print(processor.decode(output[0], skip_special_tokens=True))
+print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])
 ```
 
-</hfoption>
-</hfoptions>
+### Multi-image Inference
 
-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.
+```python
+model_id = "google/paligemma-3b-ft-nlvr2-448"  # checkpoint tuned for multiple images
+model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
+processor = PaliGemmaProcessor.from_pretrained(model_id)
 
-The example below uses [torchao](../quantization/torchao) to only quantize the weights to int4.
-
-```py
-# pip install torchao
-import torch
-import requests
-from PIL import Image
-from transformers import TorchAoConfig, AutoProcessor, PaliGemmaForConditionalGeneration
-
-quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
-model = PaliGemmaForConditionalGeneration.from_pretrained(
-    "google/paligemma2-28b-mix-224",
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    quantization_config=quantization_config
+prompt = "answer en Which of the two pictures shows a snowman, first or second?"
+stop_sign_image = Image.open(
+    requests.get("https://www.ilankelman.org/stopsigns/australia.jpg", stream=True).raw
 )
-processor = AutoProcessor.from_pretrained(
-    "google/paligemma2-28b-mix-224",
+snow_image = Image.open(
+    requests.get(
+        "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg", stream=True
+    ).raw
 )
 
-prompt = "What is in this image?"
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
-image = Image.open(requests.get(url, stream=True).raw)
-inputs = processor(image, prompt, return_tensors="pt").to("cuda")
+inputs = processor(images=[[snow_image, stop_sign_image]], text=prompt, return_tensors="pt")
+
+output = model.generate(**inputs, max_new_tokens=20)
+print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])
 
-output = model.generate(**inputs, max_new_tokens=50, cache_implementation="static")
-print(processor.decode(output[0], skip_special_tokens=True))
 ```
 
-Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/blob/beb9b5b02246b9b7ee81ddf938f93f44cfeaad19/src/transformers/utils/attention_visualizer.py#L139) to better understand what tokens the model can and cannot attend to.
+## Resources
 
-```py
-from transformers.utils.attention_visualizer import AttentionMaskVisualizer
+A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with PaliGemma. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
 
-visualizer = AttentionMaskVisualizer("google/paligemma2-3b-mix-224")
-visualizer("<img> What is in this image?")
-```
-
-## Notes
-
-- PaliGemma is not a conversational model and works best when fine-tuned for specific downstream tasks such as image captioning, visual question answering (VQA), object detection, and document understanding.
-- [`PaliGemmaProcessor`] can prepare images, text, and optional labels for the model. Pass the `suffix` parameter to the processor to create labels for the model during fine-tuning.
-
-    ```py
-    prompt = "What is in this image?"
-    answer = "a pallas cat"
-    inputs = processor(images=image, text=prompt, suffix=answer, return_tensors="pt")
-    ```
-- PaliGemma can support multiple input images if it is fine-tuned to accept multiple images. For example, the [NLVR2](https://huggingface.co/google/paligemma-3b-ft-nlvr2-448) checkpoint supports multiple images. Pass the images as a list to the processor.
-
-    ```py
-    import torch
-    import requests
-    from PIL import Image
-    from transformers import TorchAoConfig, AutoProcessor, PaliGemmaForConditionalGeneration
-
-    model = PaliGemmaForConditionalGeneration.from_pretrained("google/paligemma-3b-ft-nlvr2-448")
-    processor = AutoProcessor.from_pretrained("google/paligemma-3b-ft-nlvr2-448")
-
-    prompt = "Are these two images the same?"
-    cat_image = Image.open(
-        requests.get("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg", stream=True).raw
-    )
-    cow_image = Image.open(
-        requests.get(
-            "https://media.istockphoto.com/id/1192867753/photo/cow-in-berchida-beach-siniscola.jpg?s=612x612&w=0&k=20&c=v0hjjniwsMNfJSuKWZuIn8pssmD5h5bSN1peBd1CmH4=", stream=True
-        ).raw
-    )
-
-    inputs = processor(images=[[cat_image, cow_image]], text=prompt, return_tensors="pt")
-
-    output = model.generate(**inputs, max_new_tokens=20, cache_implementation="static")
-    print(processor.decode(output[0], skip_special_tokens=True))
-    ```
+- A blog post introducing all the features of PaliGemma can be found [here](https://huggingface.co/blog/paligemma).
+- Demo notebooks on how to fine-tune PaliGemma for VQA with the Trainer API along with inference can be found [here](https://github.com/huggingface/notebooks/tree/main/examples/paligemma).
+- Demo notebooks on how to fine-tune PaliGemma on a custom dataset (receipt image -> JSON) along with inference can be found [here](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/PaliGemma). 🌎
 
 ## PaliGemmaConfig
 

docs/source/en/model_doc/phi4_multimodal.md

@@ -1,149 +0,0 @@
-<!--Copyright 2025 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.
--->
-
-# Phi4 Multimodal
-
-## Overview
-
-Phi4 Multimodal is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning, direct preference optimization and RLHF (Reinforcement Learning from Human Feedback) to support precise instruction adherence and safety measures. The languages that each modal supports are the following:
-
-- Text: Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian
-- Vision: English
-- Audio: English, Chinese, German, French, Italian, Japanese, Spanish, Portuguese
-
-This model was contributed by [Cyril Vallez](https://huggingface.co/cyrilvallez). The most recent code can be
-found [here](https://github.com/huggingface/transformers/blob/main/src/transformers/models/phi4_multimodal/modeling_phi4_multimodal.py).
-
-
-## Usage tips
-
-`Phi4-multimodal-instruct` can be found on the [Huggingface Hub](https://huggingface.co/microsoft/Phi-4-multimodal-instruct)
-
-In the following, we demonstrate how to use it for inference depending on the input modalities (text, image, audio).
-
-```python
-import requests
-import torch
-import os
-import io
-from PIL import Image
-import soundfile as sf
-from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
-from urllib.request import urlopen
-
-
-# Define model path
-model_path = "microsoft/Phi-4-multimodal-instruct"
-device = "cuda:0"
-
-# Load model and processor
-processor = AutoProcessor.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device,  torch_dtype=torch.float16)
-
-# Optional: load the adapters (note that without them, the base model will very likely not work well)
-model.load_adapter(model_path, adapter_name="speech", device_map=device, adapter_kwargs={"subfolder": 'speech-lora'})
-model.load_adapter(model_path, adapter_name="vision", device_map=device, adapter_kwargs={"subfolder": 'vision-lora'})
-
-# Define prompt structure
-user_prompt = '<|user|>'
-assistant_prompt = '<|assistant|>'
-prompt_suffix = '<|end|>'
-
-# Part 1: Image Processing
-model.set_adapter("vision") # if loaded, activate the vision adapter
-print("\n--- IMAGE PROCESSING ---")
-image_url = 'https://www.ilankelman.org/stopsigns/australia.jpg'
-prompt = f'{user_prompt}<|image_1|>What is shown in this image?{prompt_suffix}{assistant_prompt}'
-print(f'>>> Prompt\n{prompt}')
-
-# Download and open image
-image = Image.open(requests.get(image_url, stream=True).raw)
-inputs = processor(text=prompt, images=image, return_tensors='pt').to(device)
-
-# Generate response
-generate_ids = model.generate(
-    **inputs,
-    max_new_tokens=1000,
-    do_sample=False,
-)
-generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
-response = processor.batch_decode(
-    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
-)[0]
-print(f'>>> Response\n{response}')
-
-# Part 2: Audio Processing
-model.set_adapter("speech") # if loaded, activate the speech adapter
-print("\n--- AUDIO PROCESSING ---")
-audio_url = "https://upload.wikimedia.org/wikipedia/commons/b/b0/Barbara_Sahakian_BBC_Radio4_The_Life_Scientific_29_May_2012_b01j5j24.flac"
-speech_prompt = "Transcribe the audio to text, and then translate the audio to French. Use <sep> as a separator between the original transcript and the translation."
-prompt = f'{user_prompt}<|audio_1|>{speech_prompt}{prompt_suffix}{assistant_prompt}'
-print(f'>>> Prompt\n{prompt}')
-
-# Downlowd and open audio file
-audio, sample_rate = sf.read(io.BytesIO(urlopen(audio_url).read()))
-
-# Process with the model
-inputs = processor(text=prompt, audios=audio, sample_rate=sample_rate, return_tensors='pt').to(device)
-
-generate_ids = model.generate(
-    **inputs,
-    max_new_tokens=1000,
-    do_sample=False,
-)
-generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
-response = processor.batch_decode(
-    generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
-)[0]
-print(f'>>> Response\n{response}')
-```
-
-## Phi4MultimodalFeatureExtractor
-
-[[autodoc]] Phi4MultimodalFeatureExtractor
-
-## Phi4MultimodalImageProcessorFast
-
-[[autodoc]] Phi4MultimodalImageProcessorFast
-
-## Phi4MultimodalProcessor
-
-[[autodoc]] Phi4MultimodalProcessor
-
-## Phi4MultimodalAudioConfig
-
-[[autodoc]] Phi4MultimodalAudioConfig
-
-## Phi4MultimodalVisionConfig
-
-[[autodoc]] Phi4MultimodalVisionConfig
-
-## Phi4MultimodalConfig
-
-[[autodoc]] Phi4MultimodalConfig
-
-## Phi4MultimodalAudioModel
-
-[[autodoc]] Phi4MultimodalAudioModel
-
-## Phi4MultimodalVisionModel
-
-[[autodoc]] Phi4MultimodalVisionModel
-
-## Phi4MultimodalModel
-
-[[autodoc]] Phi4MultimodalModel
-    - forward
-
-## Phi4MultimodalForCausalLM
-
-[[autodoc]] Phi4MultimodalForCausalLM
-    - forward

docs/source/en/model_doc/prompt_depth_anything.md

@@ -1,96 +0,0 @@
-<!--Copyright 2024 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.
-
--->
-
-# Prompt Depth Anything
-
-## Overview
-
-The Prompt Depth Anything model was introduced in [Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation](https://arxiv.org/abs/2412.14015) by Haotong Lin, Sida Peng, Jingxiao Chen, Songyou Peng, Jiaming Sun, Minghuan Liu, Hujun Bao, Jiashi Feng, Xiaowei Zhou, Bingyi Kang. 
-
-
-The abstract from the paper is as follows:
-
-*Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation models, creating a new paradigm for metric depth estimation termed Prompt Depth Anything. Specifically, we use a low-cost LiDAR as the prompt to guide the Depth Anything model for accurate metric depth output, achieving up to 4K resolution. Our approach centers on a concise prompt fusion design that integrates the LiDAR at multiple scales within the depth decoder. To address training challenges posed by limited datasets containing both LiDAR depth and precise GT depth, we propose a scalable data pipeline that includes synthetic data LiDAR simulation and real data pseudo GT depth generation. Our approach sets new state-of-the-arts on the ARKitScenes and ScanNet++ datasets and benefits downstream applications, including 3D reconstruction and generalized robotic grasping.*
-
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/prompt_depth_anything_architecture.jpg"
-alt="drawing" width="600"/>
-
-<small> Prompt Depth Anything overview. Taken from the <a href="https://arxiv.org/pdf/2412.14015">original paper</a>.</small>
-
-## Usage example
-
-The Transformers library allows you to use the model with just a few lines of code:
-
-```python
->>> import torch
->>> import requests
->>> import numpy as np
-
->>> from PIL import Image
->>> from transformers import AutoImageProcessor, AutoModelForDepthEstimation
-
->>> url = "https://github.com/DepthAnything/PromptDA/blob/main/assets/example_images/image.jpg?raw=true"
->>> image = Image.open(requests.get(url, stream=True).raw)
-
->>> image_processor = AutoImageProcessor.from_pretrained("depth-anything/prompt-depth-anything-vits-hf")
->>> model = AutoModelForDepthEstimation.from_pretrained("depth-anything/prompt-depth-anything-vits-hf")
-
->>> prompt_depth_url = "https://github.com/DepthAnything/PromptDA/blob/main/assets/example_images/arkit_depth.png?raw=true"
->>> prompt_depth = Image.open(requests.get(prompt_depth_url, stream=True).raw)
->>> # the prompt depth can be None, and the model will output a monocular relative depth.
-
->>> # prepare image for the model
->>> inputs = image_processor(images=image, return_tensors="pt", prompt_depth=prompt_depth)
-
->>> with torch.no_grad():
-...     outputs = model(**inputs)
-
->>> # interpolate to original size
->>> post_processed_output = image_processor.post_process_depth_estimation(
-...     outputs,
-...     target_sizes=[(image.height, image.width)],
-... )
-
->>> # visualize the prediction
->>> predicted_depth = post_processed_output[0]["predicted_depth"]
->>> depth = predicted_depth * 1000 
->>> depth = depth.detach().cpu().numpy()
->>> depth = Image.fromarray(depth.astype("uint16")) # mm
-```
-
-## Resources
-
-A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with Prompt Depth Anything.
-
-- [Prompt Depth Anything Demo](https://huggingface.co/spaces/depth-anything/PromptDA)
-- [Prompt Depth Anything Interactive Results](https://promptda.github.io/interactive.html)
-
-If you are interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
-
-## PromptDepthAnythingConfig
-
-[[autodoc]] PromptDepthAnythingConfig
-
-## PromptDepthAnythingForDepthEstimation
-
-[[autodoc]] PromptDepthAnythingForDepthEstimation
-    - forward
-
-## PromptDepthAnythingImageProcessor
-
-[[autodoc]] PromptDepthAnythingImageProcessor
-    - preprocess
-    - post_process_depth_estimation

docs/source/en/model_doc/qwen2_audio.md

@@ -29,7 +29,7 @@ The Qwen2-Audio is the new model series of large audio-language models from the
 * voice chat: users can freely engage in voice interactions with Qwen2-Audio without text input
 * audio analysis: users could provide audio and text instructions for analysis during the interaction
 
-It was proposed in [Qwen2-Audio Technical Report](https://arxiv.org/abs/2407.10759) by Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, Jingren Zhou.
+It was proposed in [Qwen2-Audio Technical Report](https://arxiv.org/abs/2407.10759) by Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, Jingren Zhou. 
 
 The abstract from the paper is the following:
 
@@ -100,7 +100,7 @@ for message in conversation:
         for ele in message["content"]:
             if ele["type"] == "audio":
                 audios.append(librosa.load(
-                    BytesIO(urlopen(ele['audio_url']).read()),
+                    BytesIO(urlopen(ele['audio_url']).read()), 
                     sr=processor.feature_extractor.sampling_rate)[0]
                 )
 
@@ -125,7 +125,7 @@ processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
 model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")
 
 conversation = [
-    {'role': 'system', 'content': 'You are a helpful assistant.'},
+    {'role': 'system', 'content': 'You are a helpful assistant.'}, 
     {"role": "user", "content": [
         {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/glass-breaking-151256.mp3"},
         {"type": "text", "text": "What's that sound?"},
@@ -148,7 +148,7 @@ for message in conversation:
             if ele["type"] == "audio":
                 audios.append(
                     librosa.load(
-                        BytesIO(urlopen(ele['audio_url']).read()),
+                        BytesIO(urlopen(ele['audio_url']).read()), 
                         sr=processor.feature_extractor.sampling_rate)[0]
                 )
 
@@ -203,7 +203,7 @@ for conversation in conversations:
                 if ele["type"] == "audio":
                     audios.append(
                         librosa.load(
-                            BytesIO(urlopen(ele['audio_url']).read()),
+                            BytesIO(urlopen(ele['audio_url']).read()), 
                             sr=processor.feature_extractor.sampling_rate)[0]
                     )
 
@@ -221,7 +221,7 @@ response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_
 
 [[autodoc]] Qwen2AudioConfig
 
-## Qwen2AudioEncoderConfig
+## Qwen2AudioConfig
 
 [[autodoc]] Qwen2AudioEncoderConfig
 
@@ -229,11 +229,6 @@ response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_
 
 [[autodoc]] Qwen2AudioProcessor
 
-## Qwen2AudioEncoder
-
-[[autodoc]] Qwen2AudioEncoder
-    - forward
-
 ## Qwen2AudioForConditionalGeneration
 
 [[autodoc]] Qwen2AudioForConditionalGeneration

docs/source/en/model_doc/shieldgemma2.md

@@ -1,100 +0,0 @@
-
-<!--Copyright 2025 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.
-
--->
-
-# ShieldGemma 2
-
-## Overview
-
-The ShieldGemma 2 model was proposed in a forthcoming technical report by Google. ShieldGemma 2 is built on [Gemma 3](https://ai.google.dev/gemma/docs/core/model_card_3), is a 4 billion (4B) parameter model that checks the safety of both synthetic and natural images against key categories to help you build robust datasets and models. With this addition to the Gemma family of models, researchers and developers can now easily minimize the risk of harmful content in their models across key areas of harm as defined below:
-
--   No Sexually Explicit content: The image shall not contain content that depicts explicit or graphic sexual acts (e.g., pornography, erotic nudity, depictions of rape or sexual assault).
--   No Dangerous Content: The image shall not contain content that facilitates or encourages activities that could cause real-world harm (e.g., building firearms and explosive devices, promotion of terrorism, instructions for suicide).
--   No Violence/Gore content: The image shall not contain content that depicts shocking, sensational, or gratuitous violence (e.g., excessive blood and gore, gratuitous violence against animals, extreme injury or moment of death).
-
-We recommend using ShieldGemma 2 as an input filter to vision language models, or as an output filter of image generation systems. To train a robust image safety model, we curated training datasets of natural and synthetic images and instruction-tuned Gemma 3 to demonstrate strong performance.
-
-This model was contributed by [Ryan Mullins](https://huggingface.co/RyanMullins).
-
-## Usage Example
-
-- ShieldGemma 2 provides a Processor that accepts a list of `images` and an optional list of `policies` as input, and constructs a batch of prompts as the product of these two lists using the provided chat template.
-- You can extend ShieldGemma's built-in in policies with the `custom_policies` argument to the Processor. Using the same key as one of the built-in policies will overwrite that policy with your custom defintion.
-- ShieldGemma 2 does not support the image cropping capabilities used by Gemma 3.
-
-### Classification against Built-in Policies
-
-```python
-from PIL import Image
-import requests
-from transformers import AutoProcessor, ShieldGemma2ForImageClassification
-
-model_id = "google/shieldgemma-2-4b-it"
-model = ShieldGemma2ForImageClassification.from_pretrained(model_id, device_map="auto")
-processor = AutoProcessor.from_pretrained(model_id)
-
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"
-image = Image.open(requests.get(url, stream=True).raw)
-
-inputs = processor(images=[image], return_tensors="pt").to(model.device)
-
-output = model(**inputs)
-print(output.probabilities)
-```
-
-### Classification against Custom Policies
-
-```python
-from PIL import Image
-import requests
-from transformers import AutoProcessor, ShieldGemma2ForImageClassification
-
-model_id = "google/shieldgemma-2-4b-it"
-model = ShieldGemma2ForImageClassification.from_pretrained(model_id, device_map="auto")
-processor = AutoProcessor.from_pretrained(model_id)
-
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"
-image = Image.open(requests.get(url, stream=True).raw)
-
-custom_policies = {
-    "key_a": "descrition_a",
-    "key_b": "descrition_b",
-}
-
-inputs = processor(
-    images=[image],
-    custom_policies=custom_policies,
-    policies=["dangerous", "key_a", "key_b"],
-    return_tensors="pt",
-).to(model.device)
-
-output = model(**inputs)
-print(output.probabilities)
-```
-
-
-## ShieldGemma2Processor
-
-[[autodoc]] ShieldGemma2Processor
-
-## ShieldGemma2Config
-
-[[autodoc]] ShieldGemma2Config
-
-## ShieldGemma2ForImageClassification
-
-[[autodoc]] ShieldGemma2ForImageClassification
-    - forward

docs/source/en/model_doc/videomae.md

@@ -18,7 +18,6 @@ rendered properly in your Markdown viewer.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/vit.md

@@ -14,83 +14,143 @@ 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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&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="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
-    </div>
-</div>
-
 # Vision Transformer (ViT)
 
-[Vision Transformer (ViT)](https://huggingface.co/papers/2010.11929) is a transformer adapted for computer vision tasks. An image is split into smaller fixed-sized patches which are treated as a sequence of tokens, similar to words for NLP tasks. ViT requires less resources to pretrain compared to convolutional architectures and its performance on large datasets can be transferred to smaller downstream tasks.
+<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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&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="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
+</div>
 
-You can find all the original ViT checkpoints under the [Google](https://huggingface.co/google?search_models=vit) organization.
+## Overview
 
-> [!TIP]
-> Click on the ViT models in the right sidebar for more examples of how to apply ViT to different computer vision tasks.
+The Vision Transformer (ViT) model was proposed in [An Image is Worth 16x16 Words: Transformers for Image Recognition
+at Scale](https://arxiv.org/abs/2010.11929) by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk
+Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob
+Uszkoreit, Neil Houlsby. It's the first paper that successfully trains a Transformer encoder on ImageNet, attaining
+very good results compared to familiar convolutional architectures.
 
-The example below demonstrates how to classify an image with [`Pipeline`] or the [`AutoModel`] class.
+The abstract from the paper is the following:
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+*While the Transformer architecture has become the de-facto standard for natural language processing tasks, its
+applications to computer vision remain limited. In vision, attention is either applied in conjunction with
+convolutional networks, or used to replace certain components of convolutional networks while keeping their overall
+structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to
+sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of
+data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.),
+Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring
+substantially fewer computational resources to train.*
 
-```py
-import torch
-from transformers import pipeline
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/vit_architecture.jpg"
+alt="drawing" width="600"/>
 
-pipeline = pipeline(
-    task="image-classification",
-    model="google/vit-base-patch16-224",
-    torch_dtype=torch.float16,
-    device=0
-)
-pipeline(images="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg")
+<small> ViT architecture. Taken from the <a href="https://arxiv.org/abs/2010.11929">original paper.</a> </small>
+
+Following the original Vision Transformer, some follow-up works have been made:
+
+- [DeiT](deit) (Data-efficient Image Transformers) by Facebook AI. DeiT models are distilled vision transformers.
+  The authors of DeiT also released more efficiently trained ViT models, which you can directly plug into [`ViTModel`] or
+  [`ViTForImageClassification`]. There are 4 variants available (in 3 different sizes): *facebook/deit-tiny-patch16-224*,
+  *facebook/deit-small-patch16-224*, *facebook/deit-base-patch16-224* and *facebook/deit-base-patch16-384*. Note that one should
+  use [`DeiTImageProcessor`] in order to prepare images for the model.
+
+- [BEiT](beit) (BERT pre-training of Image Transformers) by Microsoft Research. BEiT models outperform supervised pre-trained
+  vision transformers using a self-supervised method inspired by BERT (masked image modeling) and based on a VQ-VAE.
+
+- DINO (a method for self-supervised training of Vision Transformers) by Facebook AI. Vision Transformers trained using
+  the DINO method show very interesting properties not seen with convolutional models. They are capable of segmenting
+  objects, without having ever been trained to do so. DINO checkpoints can be found on the [hub](https://huggingface.co/models?other=dino).
+
+- [MAE](vit_mae) (Masked Autoencoders) by Facebook AI. By pre-training Vision Transformers to reconstruct pixel values for a high portion
+  (75%) of masked patches (using an asymmetric encoder-decoder architecture), the authors show that this simple method outperforms
+  supervised pre-training after fine-tuning.
+
+This model was contributed by [nielsr](https://huggingface.co/nielsr). The original code (written in JAX) can be
+found [here](https://github.com/google-research/vision_transformer).
+
+Note that we converted the weights from Ross Wightman's [timm library](https://github.com/rwightman/pytorch-image-models),
+who already converted the weights from JAX to PyTorch. Credits go to him!
+
+## Usage tips
+
+- To feed images to the Transformer encoder, each image is split into a sequence of fixed-size non-overlapping patches,
+  which are then linearly embedded. A [CLS] token is added to serve as representation of an entire image, which can be
+  used for classification. The authors also add absolute position embeddings, and feed the resulting sequence of
+  vectors to a standard Transformer encoder.
+- As the Vision Transformer expects each image to be of the same size (resolution), one can use
+  [`ViTImageProcessor`] to resize (or rescale) and normalize images for the model.
+- Both the patch resolution and image resolution used during pre-training or fine-tuning are reflected in the name of
+  each checkpoint. For example, `google/vit-base-patch16-224` refers to a base-sized architecture with patch
+  resolution of 16x16 and fine-tuning resolution of 224x224. All checkpoints can be found on the [hub](https://huggingface.co/models?search=vit).
+- The available checkpoints are either (1) pre-trained on [ImageNet-21k](http://www.image-net.org/) (a collection of
+  14 million images and 21k classes) only, or (2) also fine-tuned on [ImageNet](http://www.image-net.org/challenges/LSVRC/2012/) (also referred to as ILSVRC 2012, a collection of 1.3 million
+  images and 1,000 classes).
+- The Vision Transformer was pre-trained using a resolution of 224x224. During fine-tuning, it is often beneficial to
+  use a higher resolution than pre-training [(Touvron et al., 2019)](https://arxiv.org/abs/1906.06423), [(Kolesnikov
+  et al., 2020)](https://arxiv.org/abs/1912.11370). In order to fine-tune at higher resolution, the authors perform
+  2D interpolation of the pre-trained position embeddings, according to their location in the original image.
+- The best results are obtained with supervised pre-training, which is not the case in NLP. The authors also performed
+  an experiment with a self-supervised pre-training objective, namely masked patched prediction (inspired by masked
+  language modeling). With this approach, the smaller ViT-B/16 model achieves 79.9% accuracy on ImageNet, a significant
+  improvement of 2% to training from scratch, but still 4% behind supervised pre-training.
+
+### Using Scaled Dot Product Attention (SDPA)
+
+PyTorch includes a native scaled dot-product attention (SDPA) operator as part of `torch.nn.functional`. This function 
+encompasses several implementations that can be applied depending on the inputs and the hardware in use. See the 
+[official documentation](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) 
+or the [GPU Inference](https://huggingface.co/docs/transformers/main/en/perf_infer_gpu_one#pytorch-scaled-dot-product-attention)
+page for more information.
+
+SDPA is used by default for `torch>=2.1.1` when an implementation is available, but you may also set 
+`attn_implementation="sdpa"` in `from_pretrained()` to explicitly request SDPA to be used.
+
+```
+from transformers import ViTForImageClassification
+model = ViTForImageClassification.from_pretrained("google/vit-base-patch16-224", attn_implementation="sdpa", torch_dtype=torch.float16)
+...
 ```
 
-</hfoption>
-<hfoption id="AutoModel">
+For the best speedups, we recommend loading the model in half-precision (e.g. `torch.float16` or `torch.bfloat16`).
 
-```py
-import torch
-import requests
-from PIL import Image
-from transformers import AutoModelForImageClassification, AutoImageProcessor
+On a local benchmark (A100-40GB, PyTorch 2.3.0, OS Ubuntu 22.04) with `float32` and `google/vit-base-patch16-224` model, we saw the following speedups during inference.
 
-image_processor = AutoImageProcessor.from_pretrained(
-    "google/vit-base-patch16-224",
-    use_fast=True,
-)
-model = AutoModelForImageClassification.from_pretrained(
-    "google/vit-base-patch16-224",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    attn_implementation="sdpa"
-)
-url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
-image = Image.open(requests.get(url, stream=True).raw)
-inputs = image_processor(image, return_tensors="pt").to("cuda")
+|   Batch size |   Average inference time (ms), eager mode |   Average inference time (ms), sdpa model |   Speed up, Sdpa / Eager (x) |
+|--------------|-------------------------------------------|-------------------------------------------|------------------------------|
+|            1 |                                         7 |                                         6 |                      1.17 |
+|            2 |                                         8 |                                         6 |                      1.33 |
+|            4 |                                         8 |                                         6 |                      1.33 |
+|            8 |                                         8 |                                         6 |                      1.33 |
 
-with torch.no_grad():
-  logits = model(**inputs).logits
-predicted_class_id = logits.argmax(dim=-1).item()
+## Resources
 
-class_labels = model.config.id2label
-predicted_class_label = class_labels[predicted_class_id]
-print(f"The predicted class label is: {predicted_class_label}")
-```
+Demo notebooks regarding inference as well as fine-tuning ViT on custom data can be found [here](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/VisionTransformer).
+A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with ViT. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
 
-</hfoption>
-</hfoptions>
+`ViTForImageClassification` is supported by:
+<PipelineTag pipeline="image-classification"/>
 
-## Notes
+- A blog post on how to [Fine-Tune ViT for Image Classification with Hugging Face Transformers](https://huggingface.co/blog/fine-tune-vit)
+- A blog post on [Image Classification with Hugging Face Transformers and `Keras`](https://www.philschmid.de/image-classification-huggingface-transformers-keras)
+- A notebook on [Fine-tuning for Image Classification with Hugging Face Transformers](https://github.com/huggingface/notebooks/blob/main/examples/image_classification.ipynb)
+- A notebook on how to [Fine-tune the Vision Transformer on CIFAR-10 with the Hugging Face Trainer](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_the_%F0%9F%A4%97_Trainer.ipynb)
+- A notebook on how to [Fine-tune the Vision Transformer on CIFAR-10 with PyTorch Lightning](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Fine_tuning_the_Vision_Transformer_on_CIFAR_10_with_PyTorch_Lightning.ipynb)
 
-- The best results are obtained with supervised pretraining, and during fine-tuning, it may be better to use images with a resolution higher than 224x224.
-- Use [`ViTImageProcessorFast`] to resize (or rescale) and normalize images to the expected size.
-- The patch and image resolution are reflected in the checkpoint name. For example, google/vit-base-patch16-224, is the **base-sized** architecture with a patch resolution of 16x16 and fine-tuning resolution of 224x224.
+⚗️ Optimization
+
+- A blog post on how to [Accelerate Vision Transformer (ViT) with Quantization using Optimum](https://www.philschmid.de/optimizing-vision-transformer)
+
+⚡️ Inference
+
+- A notebook on [Quick demo: Vision Transformer (ViT) by Google Brain](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/VisionTransformer/Quick_demo_of_HuggingFace_version_of_Vision_Transformer_inference.ipynb)
+
+🚀 Deploy
+
+- A blog post on [Deploying Tensorflow Vision Models in Hugging Face with TF Serving](https://huggingface.co/blog/tf-serving-vision)
+- A blog post on [Deploying Hugging Face ViT on Vertex AI](https://huggingface.co/blog/deploy-vertex-ai)
+- A blog post on [Deploying Hugging Face ViT on Kubernetes with TF Serving](https://huggingface.co/blog/deploy-tfserving-kubernetes)
 
 ## ViTConfig
 
@@ -111,6 +171,9 @@ print(f"The predicted class label is: {predicted_class_label}")
 [[autodoc]] ViTImageProcessorFast
     - preprocess
 
+<frameworkcontent>
+<pt>
+
 ## ViTModel
 
 [[autodoc]] ViTModel
@@ -126,6 +189,9 @@ print(f"The predicted class label is: {predicted_class_label}")
 [[autodoc]] ViTForImageClassification
     - forward
 
+</pt>
+<tf>
+
 ## TFViTModel
 
 [[autodoc]] TFViTModel
@@ -136,6 +202,9 @@ print(f"The predicted class label is: {predicted_class_label}")
 [[autodoc]] TFViTForImageClassification
     - call
 
+</tf>
+<jax>
+
 ## FlaxVitModel
 
 [[autodoc]] FlaxViTModel
@@ -145,3 +214,6 @@ print(f"The predicted class label is: {predicted_class_label}")
 
 [[autodoc]] FlaxViTForImageClassification
     - __call__
+
+</jax>
+</frameworkcontent>

docs/source/en/model_doc/vit_mae.md

@@ -19,7 +19,6 @@ rendered properly in your Markdown viewer.
 <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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white">
-<img alt="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/vit_msn.md

@@ -18,7 +18,6 @@ rendered properly in your Markdown viewer.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/vivit.md

@@ -14,7 +14,6 @@ specific language governing permissions and limitations under the License.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/model_doc/whisper.md

@@ -14,86 +14,152 @@ 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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&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">
-        <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
-    </div>
-</div>
-
 # Whisper
 
-[Whisper](https://hf.co/papers/2212.04356) is a encoder-decoder (sequence-to-sequence) transformer pretrained on 680,000 hours of labeled audio data. This amount of pretraining data enables zero-shot performance on audio tasks in English and many other languages. The decoder allows Whisper to map the encoders learned speech representations to useful outputs, such as text, without additional fine-tuning. Whisper just works out of the box.
+<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="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&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">
+<img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
+</div>
 
-You can find all the original Whisper checkpoints under the [Whisper](https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715fd953013) collection.
+## Overview
 
-> [!TIP]
-> Click on the Whisper models in the right sidebar for more examples of how to apply Whisper to different audio tasks.
+The Whisper model was proposed in [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf) by Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever.
 
-The example below demonstrates how to automatically transcribe speech into text with [`Pipeline`] or the [`AutoModel`] class.
+The abstract from the paper is the following:
 
-<hfoptions id="usage">
-<hfoption id="Pipeline">
+*We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zeroshot transfer setting without the need for any finetuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.*
+
+This model was contributed by [Arthur Zucker](https://huggingface.co/ArthurZ). The Tensorflow version of this model was contributed by [amyeroberts](https://huggingface.co/amyeroberts).
+The original code can be found [here](https://github.com/openai/whisper).
+
+## Quick usage
+
+You can run Whisper in less than 4 lines of code and transcribe in less than a minute!
+
+```python
+# pip install transformers torch
 
-```py
 import torch
 from transformers import pipeline
 
-pipeline = pipeline(
-    task="automatic-speech-recognition",
-    model="openai/whisper-large-v3-turbo",
-    torch_dtype=torch.float16,
-    device=0
-)
-pipeline("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
+whisper = pipeline("automatic-speech-recognition", "openai/whisper-large-v3", torch_dtype=torch.float16, device="cuda:0")
+
+transcription = whisper("<audio_file.mp3>")
+
+print(transcription["text"])
 ```
 
-</hfoption>
-<hfoption id="AutoModel">
+Voila! You can swap the model with any [Whisper checkpoints](https://huggingface.co/models?other=whisper&sort=downloads) on the Hugging Face Hub with the same pipeline based on your needs.
 
-```py
-# pip install datasets
-import torch
-from datasets import load_dataset
-from transformers import AutoProcessor, WhisperForConditionalGeneration
+Bonus: You can replace `"cuda"` with `"mps"` to make it seamlessly work on Macs.
 
-processor = AutoProcessor.from_pretrained(
-    "openai/whisper-large-v3-turbo",
-)
-model = WhisperForConditionalGeneration.from_pretrained(
-    "openai/whisper-large-v3-turbo",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    attn_implementation="sdpa"
-).to("cuda")
+## Usage tips
 
-ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
-audio_sample = ds[0]["audio"]
+- The model usually performs well without requiring any finetuning.
+- The architecture follows a classic encoder-decoder architecture, which means that it relies on the [`~generation.GenerationMixin.generate`] function for inference.
+- One can use [`WhisperProcessor`] to prepare audio for the model, and decode the predicted ID's back into text.
 
-input_features = processor(
-    audio_sample["array"],
-    sampling_rate=audio_sample["sampling_rate"],
-    return_tensors="pt"
-).input_features
-input_features = input_features.to("cuda", dtype=torch.float16)
+- To convert the model and the processor, we recommend using the following:
 
-predicted_ids = model.generate(input_features, cache_implementation="static")
-transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-transcription[0]
+```bash
+python src/transformers/models/whisper/convert_openai_to_hf.py --checkpoint_path "" --pytorch_dump_folder_path "Arthur/whisper-3" --convert_preprocessor True
+```
+The script will automatically determine all necessary parameters from the OpenAI checkpoint. A `tiktoken` library needs to be installed
+to perform the conversion of the OpenAI tokenizer to the `tokenizers` version.
+
+## Inference
+
+Here is a step-by-step guide to transcribing an audio sample using a pre-trained Whisper model:
+
+```python
+>>> from datasets import load_dataset
+>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
+
+>>> # Select an audio file and read it:
+>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+>>> audio_sample = ds[0]["audio"]
+
+>>> # Load the Whisper model in Hugging Face format:
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
+
+>>> # Use the model and processor to transcribe the audio:
+>>> input_features = processor(
+...     audio_sample["array"], sampling_rate=audio_sample["sampling_rate"], return_tensors="pt"
+... ).input_features
+
+>>> # Generate token ids
+>>> predicted_ids = model.generate(input_features)
+
+>>> # Decode token ids to text
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+
+>>> transcription[0]
+' Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.'
 ```
 
-</hfoption>
-</hfoptions>
+Whisper is compatible with the following optimisations for both short and long-form generation:
+- [PyTorch Scaled Dot Product Attention (SDPA)](../perf_infer_gpu_one#pytorch-scaled-dot-product-attention): flash attention and memory-efficient attention kernels. Enabled by default for `torch>=2.1.1`.
+- [Flash Attention 2](../perf_infer_gpu_one#flashattention-2): improved implementation of flash attention through better parallelism and work partitioning. 
+- [torch.compile](../llm_optims#static-kv-cache-and-torchcompile): JIT-compile the forward pass to dispatch to efficient fused kernels.
 
-## Notes
+As an example, the following codesnippet enables SDPA and `torch.compile` for up to 5x faster inference:
 
-- Whisper relies on [`~GenerationMixin.generate`] for inference.
-- The [`WhisperProcessor`] can be used for preparing audio and decoding predicted ids back into text.
+```python
+>>> from datasets import load_dataset
+>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
+
+>>> # Select an audio file and read it:
+>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+>>> audio_sample = ds[0]["audio"]
+
+>>> # Load the Whisper model with SDPA attention
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en", attn_implementation="sdpa")
+
+>>> # Enable static cache and compile the forward pass
+>>> model.generation_config.cache_implementation = "static"
+>>> model.forward = torch.compile(model.forward, mode="reduce-overhead", fullgraph=True)
+
+>>> # Use the model and processor to transcribe the audio:
+>>> input_features = processor(
+...     audio_sample["array"], sampling_rate=audio_sample["sampling_rate"], return_tensors="pt"
+... ).input_features
+
+>>> # Compile the forward pass
+>>> for _ in range(2):
+>>>     model.generate(input_features)
+
+>>> # Generate token ids using compiled graph (fast!)
+>>> predicted_ids = model.generate(input_features)
+
+>>> # Decode token ids to text
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+
+>>> transcription[0]
+' Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.'
+```
+
+For more details on each optimisation, refer to the documentation linked above.
+
+## Resources
+
+A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with Whisper. If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
+
+- [Fine-tune Whisper](https://huggingface.co/blog/fine-tune-whisper) on your own dataset for better downstream performance.
+- [Distil-Whisper](https://huggingface.co/distil-whisper): Upto 6x faster, 2x smaller distilled Whisper models for English. We release the [model checkpoints](https://huggingface.co/distil-whisper), and [distillation code](https://github.com/huggingface/distil-whisper).
+- A fork with a script to [convert a Whisper model in Hugging Face format to OpenAI format](https://github.com/zuazo-forks/transformers/blob/convert_hf_to_openai/src/transformers/models/whisper/convert_hf_to_openai.py). 🌎
+Usage example:
+```bash
+pip install -U openai-whisper
+python convert_hf_to_openai.py \
+    --checkpoint openai/whisper-tiny \
+    --whisper_dump_path whisper-tiny-openai.pt
+```
 
 ## WhisperConfig
 
@@ -139,6 +205,9 @@ transcription[0]
     - batch_decode
     - decode
 
+<frameworkcontent>
+<pt>
+
 ## WhisperModel
 
 [[autodoc]] WhisperModel
@@ -161,6 +230,9 @@ transcription[0]
 [[autodoc]] WhisperForAudioClassification
     - forward
 
+</pt>
+<tf>
+
 ## TFWhisperModel
 
 [[autodoc]] TFWhisperModel
@@ -171,6 +243,9 @@ transcription[0]
 [[autodoc]] TFWhisperForConditionalGeneration
     - call
 
+</tf>
+<jax>
+
 ## FlaxWhisperModel
 
 [[autodoc]] FlaxWhisperModel
@@ -185,3 +260,7 @@ transcription[0]
 
 [[autodoc]] FlaxWhisperForAudioClassification
     - __call__
+
+</jax>
+</frameworkcontent>
+

docs/source/en/model_doc/yolos.md

@@ -18,7 +18,6 @@ rendered properly in your Markdown viewer.
 
 <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="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
 <img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
 </div>
 

docs/source/en/modular_transformers.md

@@ -78,7 +78,7 @@ class RobertaModel(BertModel):
     super().__init__(config)
     self.embeddings = RobertaEmbeddings(config)
 
-
+      
 # The model heads now only need to redefine the model inside to `RobertaModel`
 class RobertaForMaskedLM(BertForMaskedLM):
   def __init__(self, config):
@@ -546,7 +546,7 @@ This makes it very easy to switch decorators and makes it explicit that the only
 
 ## Docstring variables
 
-If an object defined in both the modular and modeling file from which it inherits, the modular definition has precedence unless for assignments containing the pattern `DOCSTRING`. These variables are typically used in `MODEL_START_DOCSTRING` and `MODEL_INPUT_DOCSTRING` in the modeling files. They are big blocks of docstrings and the linter rewrites the names everywhere. For this reason, assignments containing the `DOCSTRING` variable can use the definition found in the source file without copying the whole docstring, by simply setting the variable to `None` in the modular file.
+If an object defined in both the modular and modeling file from which it inherits, the modular definition has precedence unless for assignments containing the pattern `DOCSTRING`. These variables are typically used in `MODEL_START_DOCSTRING` and `MODEL_INPUT_DOCSTRING` in the modeling files. They are big blocks of docstrings and the linter rewrites the names everywhere. For this reason, assignments containing the `DOCSTRING` variable always uses the definition found in the source file instead of the modular file.
 
 This is very useful if you need the variable reference somewhere but you don't want to clutter the modular file with docstrings which are always the same. The example code below allows you to automatically use the same docstrings from [Mistral](./model_doc/mistral) in [Starcoder2](./model_doc/starcoder2).
 
@@ -561,8 +561,6 @@ class Starcoder2Model(MistralModel):
         ...
 ```
 
-Setting the variable to anything other than `None` will override the docstring, so that you can customize the docstrings if needed.
-
 ## Special naming
 
 The linter automatically renames everything when inheriting from a class. For consistency, you should always use the same class name prefix when inheriting from different classes from the same file.
@@ -588,7 +586,7 @@ We detected multiple prefix names when inheriting from transformers.models.llama
 If there are automatic dependencies with a prefix, but you want another one, explicitly rename the classes locally with a `pass` class as shown in the following.
 
 ```py
-class Emu3TextMLP(LlamaMLP):
+class Emu3TextMLP(LlamaMLP):                                 
     pass
 ```
 

docs/source/en/quantization/bitsandbytes.md

@@ -20,10 +20,7 @@ rendered properly in your Markdown viewer.
 
 [LLM.int8()](https://hf.co/papers/2208.07339) is a quantization method that aims to make large language model inference more accessible without significant degradation. Unlike naive 8-bit quantization, which can result in loss of critical information and accuracy, LLM.int8() dynamically adapts to ensure sensitive components of the computation retain higher precision when needed.
 
-QLoRA, or 4-bit quantization, compresses a model even further to 4-bits and inserts a small set of trainable low-rank adaptation (LoRA) weights to allowing training. 
-
-> **Note:** For a user-friendly quantization experience, you can use the `bitsandbytes` [community space](https://huggingface.co/spaces/bnb-community/bnb-my-repo).
-
+QLoRA, or 4-bit quantization, compresses a model even further to 4-bits and inserts a small set of trainable low-rank adaptation (LoRA) weights to allowing training.
 
 Run the command below to install bitsandbytes.
 

docs/source/en/quantization/overview.md

@@ -40,20 +40,10 @@ Use the Space below to help you pick a quantization method depending on your har
 | [VPTQ](./vptq)                             | 🔴                   | 🔴              |     🟢     | 🟡        | 🔴                                 | 🔴              | 🟢              | 1/8         | 🔴               | 🟢                          | 🟢                      | https://github.com/microsoft/VPTQ            |
 | [FINEGRAINED_FP8](./finegrained_fp8)                 | 🟢                   | 🔴              | 🟢        | 🔴        | 🔴                                 | 🔴              | 🔴              | 8             | 🔴               | 🟢                          | 🟢                      |        |
 | [SpQR](./spqr)                          | 🔴                       |  🔴   | 🟢        | 🔴              |    🔴    | 🔴         |         🟢              | 3              |              🔴                     | 🟢           | 🟢                      | https://github.com/Vahe1994/SpQR/       |
-| [Quark](./quark.md)                           | 🔴                       | 🟢 | 🟢      | 🟢      | 🟢                   | 🟢       | ?               | 2/4/6/8/9/16 | 🔴                | 🔴                               | 🟢                       | https://quark.docs.amd.com/latest/                      |
 
 ## Resources
 
 If you are new to quantization, we recommend checking out these beginner-friendly quantization courses in collaboration with DeepLearning.AI.
 
 * [Quantization Fundamentals with Hugging Face](https://www.deeplearning.ai/short-courses/quantization-fundamentals-with-hugging-face/)
-* [Quantization in Depth](https://www.deeplearning.ai/short-courses/quantization-in-depth)
-
-## User-Friendly Quantization Tools
-
-If you are looking for a user-friendly quantization experience, you can use the following community spaces and notebooks: 
-
-* [Bitsandbytes Space](https://huggingface.co/spaces/bnb-community/bnb-my-repo)
-* [GGUF Space](https://huggingface.co/spaces/ggml-org/gguf-my-repo)
-* [MLX Space](https://huggingface.co/spaces/mlx-community/mlx-my-repo)
-* [AuoQuant Notebook](https://colab.research.google.com/drive/1b6nqC7UZVt8bx4MksX7s656GXPM-eWw4?usp=sharing#scrollTo=ZC9Nsr9u5WhN)
+* [Quantization in Depth](https://www.deeplearning.ai/short-courses/quantization-in-depth

docs/source/en/quantization/quark.md

@@ -1,84 +0,0 @@
-<!--Copyright 2025 Advanced Micro Devices, Inc. and 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.
-
--->
-
-# Quark
-
-[Quark](https://quark.docs.amd.com/latest/) is a deep learning quantization toolkit designed to be agnostic to specific data types, algorithms, and hardware. Different pre-processing strategies, algorithms and data-types can be combined in Quark.
-
-The PyTorch support integrated through 🤗 Transformers primarily targets AMD CPUs and GPUs, and is primarily meant to be used for evaluation purposes. For example, it is possible to use [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) with 🤗 Transformers backend and evaluate a wide range of models quantized through Quark seamlessly.
-
-Users interested in Quark can refer to its [documentation](https://quark.docs.amd.com/latest/) to get started quantizing models and using them in supported open-source libraries!
-
-Although Quark has its own checkpoint / [configuration format](https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV-Quark-test/blob/main/config.json#L26), the library also supports producing models with a serialization layout compliant with other quantization/runtime implementations ([AutoAWQ](https://huggingface.co/docs/transformers/quantization/awq), [native fp8 in 🤗 Transformers](https://huggingface.co/docs/transformers/quantization/finegrained_fp8)).
-
-To be able to load Quark quantized models in Transformers, the library first needs to be installed:
-
-```bash
-pip install amd-quark
-```
-
-## Support matrix
-
-Models quantized through Quark support a large range of features, that can be combined together. All quantized models independently of their configuration can seamlessly be reloaded through `PretrainedModel.from_pretrained`.
-
-The table below shows a few features supported by Quark:
-
-| **Feature**                     | **Supported subset in Quark**                                                                             |   |
-|---------------------------------|-----------------------------------------------------------------------------------------------------------|---|
-| Data types                      | int8, int4, int2, bfloat16, float16, fp8_e5m2, fp8_e4m3, fp6_e3m2, fp6_e2m3, fp4, OCP MX, MX6, MX9, bfp16 |   |
-| Pre-quantization transformation | SmoothQuant, QuaRot, SpinQuant, AWQ                                                                       |   |
-| Quantization algorithm          | GPTQ                                                                                                      |   |
-| Supported operators             | ``nn.Linear``, ``nn.Conv2d``, ``nn.ConvTranspose2d``, ``nn.Embedding``, ``nn.EmbeddingBag``               |   |
-| Granularity                     | per-tensor, per-channel, per-block, per-layer, per-layer type                                             |   |
-| KV cache                        | fp8                                                                                                       |   |
-| Activation calibration          | MinMax / Percentile / MSE                                                                                 |   |
-| Quantization strategy           | weight-only, static, dynamic, with or without output quantization                                         |   |
-
-## Models on Hugging Face Hub
-
-Public models using Quark native serialization can be found at https://huggingface.co/models?other=quark.
-
-Although Quark also supports [models using `quant_method="fp8"`](https://huggingface.co/models?other=fp8) and [models using `quant_method="awq"`](https://huggingface.co/models?other=awq), Transformers loads these models rather through [AutoAWQ](https://huggingface.co/docs/transformers/quantization/awq) or uses the [native fp8 support in 🤗 Transformers](https://huggingface.co/docs/transformers/quantization/finegrained_fp8).
-
-## Using Quark models in Transformers
-
-Here is an example of how one can load a Quark model in Transformers:
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_id = "EmbeddedLLM/Llama-3.1-8B-Instruct-w_fp8_per_channel_sym"
-model = AutoModelForCausalLM.from_pretrained(model_id)
-model = model.to("cuda")
-
-print(model.model.layers[0].self_attn.q_proj)
-# QParamsLinear(
-#   (weight_quantizer): ScaledRealQuantizer()
-#   (input_quantizer): ScaledRealQuantizer()
-#   (output_quantizer): ScaledRealQuantizer()
-# )
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-inp = tokenizer("Where is a good place to cycle around Tokyo?", return_tensors="pt")
-inp = inp.to("cuda")
-
-res = model.generate(**inp, min_new_tokens=50, max_new_tokens=100)
-
-print(tokenizer.batch_decode(res)[0])
-# <|begin_of_text|>Where is a good place to cycle around Tokyo? There are several places in Tokyo that are suitable for cycling, depending on your skill level and interests. Here are a few suggestions:
-# 1. Yoyogi Park: This park is a popular spot for cycling and has a wide, flat path that's perfect for beginners. You can also visit the Meiji Shrine, a famous Shinto shrine located in the park.
-# 2. Imperial Palace East Garden: This beautiful garden has a large, flat path that's perfect for cycling. You can also visit the
-```

docs/source/en/quantization/torchao.md

@@ -20,95 +20,18 @@ Install torchao with the following command.
 pip install --upgrade torch torchao transformers
 ```
 
-torchao supports many quantization types for different data types (int4, float8, weight only, etc.).
-Starting with version 0.10.0, torchao provides enhanced flexibility through the `AOBaseConfig` API, allowing for more customized quantization configurations.
-And full access to the techniques offered in the torchao library.
+torchao supports many quantization types for different data types (int4, float8, weight only, etc.), but the Transformers integration only currently supports int8 weight quantization and int8 dynamic quantization of weights.
 
 You can manually choose the quantization types and settings or automatically select the quantization types.
 
 <hfoptions id="torchao">
 <hfoption id="manual">
 
-
 Create a [`TorchAoConfig`] and specify the quantization type and `group_size` of the weights to quantize. Set the `cache_implementation` to `"static"` to automatically [torch.compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) the forward method.
 
 > [!TIP]
 > Run the quantized model on a CPU by changing `device_map` to `"cpu"` and `layout` to `Int4CPULayout()`. This is only available in torchao 0.8.0+.
 
-In torchao 0.10.0+, you can use the more flexible `AOBaseConfig` approach instead of string identifiers:
-
-```py
-import torch
-from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
-from torchao.quantization import Int4WeightOnlyConfig
-
-# Using AOBaseConfig instance (torchao >= 0.10.0)
-quant_config = Int4WeightOnlyConfig(group_size=128)
-quantization_config = TorchAoConfig(quant_type=quant_config)
-
-# Load and quantize the model
-quantized_model = AutoModelForCausalLM.from_pretrained(
-    "meta-llama/Meta-Llama-3-8B",
-    torch_dtype="auto",
-    device_map="auto",
-    quantization_config=quantization_config
-)
-
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")
-input_text = "What are we having for dinner?"
-input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
-
-# auto-compile the quantized model with `cache_implementation="static"` to get speed up
-output = quantized_model.generate(**input_ids, max_new_tokens=10, cache_implementation="static")
-print(tokenizer.decode(output[0], skip_special_tokens=True))
-```
-
-## Available Quantization Schemes
-
-TorchAO provides a variety of quantization configurations:
-
-- `Int4WeightOnlyConfig`
-- `Int8WeightOnlyConfig`
-- `Int8DynamicActivationInt8WeightConfig`
-- `Float8WeightOnlyConfig`
-
-Each configuration can be further customized with parameters such as `group_size`, `scheme`, and `layout` to optimize for specific hardware and model architectures.
-
-For a complete list of available configurations, see our [quantization API documentation](https://github.com/pytorch/ao/blob/main/torchao/quantization/quant_api.py).
-
-> **⚠️ DEPRECATION WARNING**
->
-> Starting with version 0.10.0, the string-based API for quantization configuration (e.g., `TorchAoConfig("int4_weight_only", group_size=128)`) is **deprecated** and will be removed in a future release.
->
-> Please use the new `AOBaseConfig`-based approach instead:
->
-> ```python
-> # Old way (deprecated)
-> quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
->
-> # New way (recommended)
-> from torchao.quantization import Int4WeightOnlyConfig
-> quant_config = Int4WeightOnlyConfig(group_size=128)
-> quantization_config = TorchAoConfig(quant_type=quant_config)
-> ```
->
-> The new API offers greater flexibility, better type safety, and access to the full range of features available in torchao.
->
-> ## Migration Guide
->
-> Here's how to migrate from common string identifiers to their `AOBaseConfig` equivalents:
->
-> | Old String API | New `AOBaseConfig` API |
-> |----------------|------------------------|
-> | `"int4_weight_only"` | `Int4WeightOnlyConfig()` |
-> | `"int8_weight_only"` | `Int8WeightOnlyConfig()` |
-> | `"int8_dynamic_activation_int8_weight"` | `Int8DynamicActivationInt8WeightConfig()` |
->
-> All configuration objects accept parameters for customization (e.g., `group_size`, `scheme`, `layout`).
-
-
-Below is the API for for torchao < `0.9.0`
-
 ```py
 import torch
 from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
@@ -150,15 +73,12 @@ output = bf16_model.generate(**input_ids, max_new_tokens=10, cache_implementatio
 print("bf16 model:", benchmark_fn(bf16_model.generate, **input_ids, max_new_tokens=MAX_NEW_TOKENS, cache_implementation="static"))
 ```
 
-> [!TIP]
-> For best performance, you can use recommended settings by calling `torchao.quantization.utils.recommended_inductor_config_setter()`
-
 </hfoption>
 <hfoption id="automatic">
 
 The [autoquant](https://pytorch.org/ao/stable/generated/torchao.quantization.autoquant.html#torchao.quantization.autoquant) API automatically chooses a quantization type for quantizable layers (`nn.Linear`) by micro-benchmarking on input type and shape and compiling a single linear layer.
 
-Create a [`TorchAoConfig`] and set to `"autoquant"`. Set the `cache_implementation` to `"static"` to automatically [torch.compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) the forward method. Finally, call `finalize_autoquant` on the quantized model to finalize the quantization and log the input shapes.
+Create a [`TorchAoConfig`] and set to `"autoquant"`. Set the `cache_implementation` to `"static"` to automatically [torch.compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) the forward method. Finally, call `finalize_autoquant` on the quantized model to finalize the quantization and log the input shapes. 
 
 > [!TIP]
 > Run the quantized model on a CPU by changing `device_map` to `"cpu"` and `layout` to `Int4CPULayout()`. This is only available in torchao 0.8.0+.
@@ -211,7 +131,7 @@ print("bf16 model:", benchmark_fn(bf16_model.generate, **input_ids, max_new_toke
 
 ## Serialization
 
-torchao implements [torch.Tensor subclasses](https://pytorch.org/docs/stable/notes/extending.html#subclassing-torch-tensor) for maximum flexibility in supporting new quantized torch.Tensor formats. [Safetensors](https://huggingface.co/docs/safetensors/en/index) serialization and deserialization does not work with torchao.
+torchao implements [torch.Tensor subclasses](https://pytorch.org/docs/stable/notes/extending.html#subclassing-torch-tensor) for maximum flexibility in supporting new quantized torch.Tensor formats. [Safetensors](https://huggingface.co/docs/safetensors/en/index) serialization and deserialization does not work with torchaco.
 
 To avoid arbitrary user code execution, torchao sets `weights_only=True` in [torch.load](https://pytorch.org/docs/stable/generated/torch.load.html) to ensure only tensors are loaded. Any known user functions can be whitelisted with [add_safe_globals](https://pytorch.org/docs/stable/notes/serialization.html#torch.serialization.add_safe_globals).
 

docs/source/es/quicktour.md

@@ -220,7 +220,7 @@ Pasa tu texto al tokenizador:
 El tokenizador devolverá un diccionario conteniendo:
 
 * [input_ids](./glossary#input-ids): representaciones numéricas de los tokens.
-* [attention_mask](.glossary#attention-mask): indica cuáles tokens deben ser atendidos.
+* [atttention_mask](.glossary#attention-mask): indica cuáles tokens deben ser atendidos.
 
 Como con el [`pipeline`], el tokenizador aceptará una lista de inputs. Además, el tokenizador también puede rellenar (pad, en inglés) y truncar el texto para devolver un lote (batch, en inglés) de longitud uniforme:
 

docs/source/it/perf_infer_cpu.md

@@ -23,7 +23,7 @@ Abbiamo integrato di recente `BetterTransformer` per fare inferenza più rapidam
 
 ## PyTorch JIT-mode (TorchScript)
 
-TorchScript è un modo di creare modelli serializzabili e ottimizzabili da codice PyTorch. Ogni programma TorchScript può esere salvato da un processo Python  e caricato in un processo dove non ci sono dipendenze Python.
+TorchScript è un modo di creare modelli serializzabili e ottimizzabili da codice PyTorch. Ogni programmma TorchScript può esere salvato da un processo Python  e caricato in un processo dove non ci sono dipendenze Python.
 Comparandolo con l'eager mode di default, jit mode in PyTorch normalmente fornisce prestazioni migliori per l'inferenza del modello da parte di metodologie di ottimizzazione come la operator fusion.
 
 Per una prima introduzione a TorchScript, vedi la Introduction to [PyTorch TorchScript tutorial](https://pytorch.org/tutorials/beginner/Intro_to_TorchScript_tutorial.html#tracing-modules).

docs/source/ja/main_classes/optimizer_schedules.md

@@ -22,6 +22,10 @@ rendered properly in your Markdown viewer.
 - `_LRSchedule` から継承するスケジュール オブジェクトの形式のいくつかのスケジュール:
 - 複数のバッチの勾配を累積するための勾配累積クラス
 
+## AdamW (PyTorch)
+
+[[autodoc]] AdamW
+
 ## AdaFactor (PyTorch)
 
 [[autodoc]] Adafactor

docs/source/pt/quicktour.md

@@ -222,7 +222,7 @@ Passe o texto para o tokenizer:
 O tokenizer retornará um dicionário contendo:
 
 * [input_ids](./glossary#input-ids): representações numéricas de seus tokens.
-* [attention_mask](.glossary#attention-mask): indica quais tokens devem ser atendidos.
+* [atttention_mask](.glossary#attention-mask): indica quais tokens devem ser atendidos.
 
 Assim como o [`pipeline`], o tokenizer aceitará uma lista de entradas. Além disso, o tokenizer também pode preencher e truncar o texto para retornar um lote com comprimento uniforme:
 

docs/source/zh/main_classes/optimizer_schedules.md

@@ -22,6 +22,10 @@ rendered properly in your Markdown viewer.
 - 继承自 `_LRSchedule` 多个调度器：
 - 一个梯度累积类，用于累积多个批次的梯度
 
+## AdamW (PyTorch)
+
+[[autodoc]] AdamW
+
 ## AdaFactor (PyTorch)
 
 [[autodoc]] Adafactor

examples/flax/question-answering/run_qa.py

@@ -61,7 +61,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 Array = Any
 Dataset = datasets.arrow_dataset.Dataset

examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py

@@ -60,7 +60,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risk.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/flax/speech-recognition/requirements.txt")
 

examples/flax/text-classification/run_flax_glue.py

@@ -56,7 +56,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 
 logger = logging.getLogger(__name__)
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 Array = Any
 Dataset = datasets.arrow_dataset.Dataset

examples/flax/token-classification/run_flax_ner.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 logger = logging.getLogger(__name__)
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")
 

examples/legacy/pytorch-lightning/lightning_base.py

@@ -8,6 +8,7 @@ import pytorch_lightning as pl
 from pytorch_lightning.utilities import rank_zero_info
 
 from transformers import (
+    AdamW,
     AutoConfig,
     AutoModel,
     AutoModelForPreTraining,
@@ -19,7 +20,6 @@ from transformers import (
     AutoTokenizer,
     PretrainedConfig,
     PreTrainedTokenizer,
-    is_torch_available,
 )
 from transformers.optimization import (
     Adafactor,
@@ -31,10 +31,6 @@ from transformers.optimization import (
 from transformers.utils.versions import require_version
 
 
-if is_torch_available():
-    import torch
-
-
 logger = logging.getLogger(__name__)
 
 require_version("pytorch_lightning>=1.0.4")
@@ -150,7 +146,7 @@ class BaseTransformer(pl.LightningModule):
             )
 
         else:
-            optimizer = torch.optim.AdamW(
+            optimizer = AdamW(
                 optimizer_grouped_parameters, lr=self.hparams.learning_rate, eps=self.hparams.adam_epsilon
             )
         self.opt = optimizer

examples/legacy/question-answering/run_squad.py

@@ -32,6 +32,7 @@ import transformers
 from transformers import (
     MODEL_FOR_QUESTION_ANSWERING_MAPPING,
     WEIGHTS_NAME,
+    AdamW,
     AutoConfig,
     AutoModelForQuestionAnswering,
     AutoTokenizer,
@@ -95,7 +96,7 @@ def train(args, train_dataset, model, tokenizer):
         },
         {"params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], "weight_decay": 0.0},
     ]
-    optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
+    optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
     scheduler = get_linear_schedule_with_warmup(
         optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total
     )

examples/legacy/run_openai_gpt.py

@@ -43,6 +43,7 @@ from tqdm import tqdm, trange
 from transformers import (
     CONFIG_NAME,
     WEIGHTS_NAME,
+    AdamW,
     OpenAIGPTDoubleHeadsModel,
     OpenAIGPTTokenizer,
     get_linear_schedule_with_warmup,
@@ -235,7 +236,7 @@ def main():
             },
             {"params": [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], "weight_decay": 0.0},
         ]
-        optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
+        optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
         scheduler = get_linear_schedule_with_warmup(
             optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total
         )

examples/legacy/run_swag.py

@@ -34,6 +34,7 @@ from tqdm import tqdm, trange
 import transformers
 from transformers import (
     WEIGHTS_NAME,
+    AdamW,
     AutoConfig,
     AutoModelForMultipleChoice,
     AutoTokenizer,
@@ -297,7 +298,7 @@ def train(args, train_dataset, model, tokenizer):
         },
         {"params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], "weight_decay": 0.0},
     ]
-    optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
+    optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
     scheduler = get_linear_schedule_with_warmup(
         optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total
     )

examples/legacy/seq2seq/seq2seq_trainer.py

@@ -22,6 +22,7 @@ from transformers import PreTrainedModel, Trainer, logging
 from transformers.models.fsmt.configuration_fsmt import FSMTConfig
 from transformers.optimization import (
     Adafactor,
+    AdamW,
     get_constant_schedule,
     get_constant_schedule_with_warmup,
     get_cosine_schedule_with_warmup,
@@ -101,11 +102,12 @@ class Seq2SeqTrainer(Trainer):
                     "weight_decay": 0.0,
                 },
             ]
+            optimizer_cls = Adafactor if self.args.adafactor else AdamW
             if self.args.adafactor:
                 optimizer_cls = Adafactor
                 optimizer_kwargs = {"scale_parameter": False, "relative_step": False}
             else:
-                optimizer_cls = torch.optim.AdamW
+                optimizer_cls = AdamW
                 optimizer_kwargs = {
                     "betas": (self.args.adam_beta1, self.args.adam_beta2),
                     "eps": self.args.adam_epsilon,

examples/pytorch/audio-classification/run_audio_classification.py

@@ -45,7 +45,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.14.0", "To fix: pip install -r examples/pytorch/audio-classification/requirements.txt")
 

examples/pytorch/contrastive-image-text/run_clip.py

@@ -54,7 +54,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/contrastive-image-text/requirements.txt")
 

examples/pytorch/image-classification/run_image_classification.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/image-classification/requirements.txt")
 

examples/pytorch/image-classification/run_image_classification_no_trainer.py

@@ -49,7 +49,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 

examples/pytorch/image-pretraining/run_mae.py

@@ -43,7 +43,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 

examples/pytorch/image-pretraining/run_mim.py

@@ -48,7 +48,7 @@ Any model supported by the AutoModelForMaskedImageModeling API can be used.
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 

examples/pytorch/image-pretraining/run_mim_no_trainer.py

@@ -53,7 +53,7 @@ Any model supported by the AutoModelForMaskedImageModeling API can be used.
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 

examples/pytorch/instance-segmentation/run_instance_segmentation.py

@@ -46,7 +46,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/instance-segmentation/requirements.txt")
 

examples/pytorch/instance-segmentation/run_instance_segmentation_no_trainer.py

@@ -52,7 +52,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/instance-segmentation/requirements.txt")
 

examples/pytorch/language-modeling/run_clm.py

@@ -55,7 +55,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 

examples/pytorch/language-modeling/run_fim.py

@@ -58,7 +58,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/language-modeling/run_fim_no_trainer.py

@@ -60,7 +60,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 

examples/pytorch/language-modeling/run_mlm.py

@@ -54,7 +54,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")

examples/pytorch/language-modeling/run_plm.py

@@ -47,7 +47,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 

examples/pytorch/multiple-choice/run_swag.py

@@ -46,7 +46,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = logging.getLogger(__name__)
 

examples/pytorch/multiple-choice/run_swag_no_trainer.py

@@ -54,7 +54,7 @@ from transformers.utils import check_min_version, send_example_telemetry
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 # You should update this to your particular problem to have better documentation of `model_type`

examples/pytorch/object-detection/run_object_detection.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/object-detection/requirements.txt")
 

examples/pytorch/object-detection/run_object_detection_no_trainer.py

@@ -51,7 +51,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logging.basicConfig(level=logging.INFO)
 logger = get_logger(__name__)

examples/pytorch/question-answering/run_qa.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_qa_beam_search.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py

@@ -41,6 +41,7 @@ from utils_qa import postprocess_qa_predictions_with_beam_search
 
 import transformers
 from transformers import (
+    AdamW,
     DataCollatorWithPadding,
     EvalPrediction,
     SchedulerType,
@@ -55,7 +56,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 
@@ -766,7 +767,7 @@ def main():
             "weight_decay": 0.0,
         },
     ]
-    optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=args.learning_rate)
+    optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate)
 
     # Scheduler and math around the number of training steps.
     overrode_max_train_steps = False

examples/pytorch/question-answering/run_qa_no_trainer.py

@@ -57,7 +57,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/question-answering/run_seq2seq_qa.py

@@ -46,7 +46,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 

examples/pytorch/semantic-segmentation/run_semantic_segmentation.py

@@ -51,7 +51,7 @@ from transformers.utils.versions import require_version
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/semantic-segmentation/requirements.txt")
 

examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 

examples/pytorch/speech-pretraining/run_wav2vec2_pretraining_no_trainer.py

@@ -33,6 +33,7 @@ from tqdm.auto import tqdm
 
 import transformers
 from transformers import (
+    AdamW,
     SchedulerType,
     Wav2Vec2Config,
     Wav2Vec2FeatureExtractor,
@@ -582,7 +583,7 @@ def main():
     )
 
     # Optimizer
-    optimizer = torch.optim.AdamW(
+    optimizer = AdamW(
         list(model.parameters()),
         lr=args.learning_rate,
         betas=[args.adam_beta1, args.adam_beta2],

examples/pytorch/speech-recognition/run_speech_recognition_ctc.py

@@ -50,7 +50,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 

examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py

@@ -53,7 +53,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 

examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 

examples/pytorch/summarization/run_summarization.py

@@ -52,7 +52,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 

examples/pytorch/summarization/run_summarization_no_trainer.py

@@ -56,7 +56,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")

examples/pytorch/text-classification/run_classification.py

@@ -47,7 +47,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 

examples/pytorch/text-classification/run_glue.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 

examples/pytorch/text-classification/run_glue_no_trainer.py

@@ -49,7 +49,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 logger = get_logger(__name__)
 

examples/pytorch/text-classification/run_xnli.py

@@ -48,7 +48,7 @@ from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.51.0.dev0")
+check_min_version("4.50.0.dev0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")