Merge branch 'huggingface:main' into patch-1

.circleci/config.yml

@@ -43,6 +43,12 @@ jobs:
                 else
                     touch test_preparation/test_list.txt
                 fi
+            - run: |
+                if [ -f doctest_list.txt ]; then
+                    cp doctest_list.txt test_preparation/doctest_list.txt
+                else
+                    touch test_preparation/doctest_list.txt
+                fi
             - run: |
                 if [ -f test_repo_utils.txt ]; then
                     mv test_repo_utils.txt test_preparation/test_repo_utils.txt
@@ -71,6 +77,8 @@ jobs:
                   fi
             - store_artifacts:
                   path: test_preparation/test_list.txt
+            - store_artifacts:
+                  path: test_preparation/doctest_list.txt
             - store_artifacts:
                   path: ~/transformers/test_preparation/filtered_test_list.txt
             - store_artifacts:

.circleci/create_circleci_config.py

@@ -483,7 +483,6 @@ def job_name(self):
     hub_job,
     onnx_job,
     exotic_models_job,
-    doc_test_job
 ]
 EXAMPLES_TESTS = [
     examples_torch_job,
@@ -495,6 +494,8 @@ def job_name(self):
     pipelines_tf_job,
 ]
 REPO_UTIL_TESTS = [repo_utils_job]
+DOC_TESTS = [doc_test_job]
+
 
 def create_circleci_config(folder=None):
     if folder is None:
@@ -552,6 +553,15 @@ def create_circleci_config(folder=None):
     if os.path.exists(example_file) and os.path.getsize(example_file) > 0:
         jobs.extend(EXAMPLES_TESTS)
 
+    doctest_file = os.path.join(folder, "doctest_list.txt")
+    if os.path.exists(doctest_file):
+        with open(doctest_file) as f:
+            doctest_list = f.read()
+    else:
+        doctest_list = []
+    if len(doctest_list) > 0:
+        jobs.extend(DOC_TESTS)
+
     repo_util_file = os.path.join(folder, "test_repo_utils.txt")
     if os.path.exists(repo_util_file) and os.path.getsize(repo_util_file) > 0:
         jobs.extend(REPO_UTIL_TESTS)

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

@@ -71,6 +71,16 @@ jobs:
     name: "Latest PyTorch + DeepSpeed"
     runs-on: ubuntu-latest
     steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
       -
         name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
@@ -98,6 +108,16 @@ jobs:
     name: "Latest PyTorch + DeepSpeed (Push CI - Daily Build)"
     runs-on: ubuntu-latest
     steps:
+      - name: Cleanup disk
+        run: |
+          sudo ls -l /usr/local/lib/
+          sudo ls -l /usr/share/
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /usr/share/dotnet
+          sudo du -sh /usr/local/lib/
+          sudo du -sh /usr/share/
       -
         name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2

Makefile

@@ -111,3 +111,10 @@ post-release:
 
 post-patch:
 	python utils/release.py --post_release --patch
+
+build-release:
+	rm -rf dist
+	rm -rf build
+	python setup.py bdist_wheel
+	python setup.py sdist
+	python utils/check_build.py

README.md

@@ -115,6 +115,19 @@ In Multimodal tasks:
 
 **[Write With Transformer](https://transformer.huggingface.co)**, built by the Hugging Face team, is the official demo of this repo’s text generation capabilities.
 
+
+## 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!
+
 ## If you are looking for custom support from the Hugging Face team
 
 <a target="_blank" href="https://huggingface.co/support">

docker/transformers-all-latest-gpu/Dockerfile

@@ -35,7 +35,7 @@ RUN [ "$PYTORCH" != "pre" ] && python3 -m pip install --no-cache-dir -U $VERSION
 RUN python3 -m pip install --no-cache-dir -U tensorflow==2.12 protobuf==3.20.3 tensorflow_text tensorflow_probability
 RUN python3 -m pip uninstall -y flax jax
 
-RUN python3 -m pip install --no-cache-dir intel_extension_for_pytorch==$INTEL_TORCH_EXT+cpu -f https://software.intel.com/ipex-whl-stable
+RUN python3 -m pip install --no-cache-dir intel_extension_for_pytorch==$INTEL_TORCH_EXT+cpu -f https://developer.intel.com/ipex-whl-stable-cpu
 
 RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract
 RUN python3 -m pip install -U "itsdangerous<2.1.0"

docker/transformers-pytorch-deepspeed-latest-gpu/Dockerfile

@@ -1,12 +1,12 @@
 # https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_22-08.html#rel_22-08
-FROM nvcr.io/nvidia/pytorch:22.08-py3
+FROM nvcr.io/nvidia/pytorch:22.12-py3
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive
 
 ARG PYTORCH='2.0.1'
 # Example: `cu102`, `cu113`, etc.
-ARG CUDA='cu117'
+ARG CUDA='cu118'
 
 RUN apt -y update
 RUN apt install -y libaio-dev
@@ -15,6 +15,8 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip
 ARG REF=main
 RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
 
+RUN python3 -m pip uninstall -y torch torchvision torchaudio
+
 # Install latest release PyTorch
 # (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
 # (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)

docker/transformers-pytorch-deepspeed-nightly-gpu/Dockerfile

@@ -1,11 +1,11 @@
 # https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_22-08.html#rel_22-08
-FROM nvcr.io/nvidia/pytorch:22.08-py3
+FROM nvcr.io/nvidia/pytorch:22.12-py3
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive
 
 # Example: `cu102`, `cu113`, etc.
-ARG CUDA='cu117'
+ARG CUDA='cu118'
 
 RUN apt -y update
 RUN apt install -y libaio-dev
@@ -14,6 +14,8 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip
 ARG REF=main
 RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
 
+RUN python3 -m pip uninstall -y torch torchvision torchaudio
+
 # Install **nightly** release PyTorch (flag `--pre`)
 # (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
 # (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)

docker/transformers-pytorch-gpu/Dockerfile

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu20.04
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
 LABEL maintainer="Hugging Face"
 
 ARG DEBIAN_FRONTEND=noninteractive
@@ -16,7 +16,7 @@ ARG PYTORCH='2.0.1'
 ARG TORCH_VISION=''
 ARG TORCH_AUDIO=''
 # Example: `cu102`, `cu113`, etc.
-ARG CUDA='cu117'
+ARG CUDA='cu118'
 
 RUN [ ${#PYTORCH} -gt 0 ] && VERSION='torch=='$PYTORCH'.*' ||  VERSION='torch'; python3 -m pip install --no-cache-dir -U $VERSION --extra-index-url https://download.pytorch.org/whl/$CUDA
 RUN [ ${#TORCH_VISION} -gt 0 ] && VERSION='torchvision=='TORCH_VISION'.*' ||  VERSION='torchvision'; python3 -m pip install --no-cache-dir -U $VERSION --extra-index-url https://download.pytorch.org/whl/$CUDA

docs/source/en/generation_strategies.mdx

@@ -338,9 +338,8 @@ For the complete list of the available parameters, refer to the [API documentati
 Assisted decoding is a modification of the decoding strategies above that uses an assistant model with the same
 tokenizer (ideally a much smaller model) to greedily generate a few candidate tokens. The main model then validates
 the candidate tokens in a single forward pass, which speeds up the decoding process. Currently, only greedy search
-and sampling are supported with assisted decoding, and doesn't support batched inputs.
-
-<!-- TODO: add link to the blog post about assisted decoding when it exists -->
+and sampling are supported with assisted decoding, and doesn't support batched inputs. To learn more about assisted
+decoding, check [this blog post](https://huggingface.co/blog/assisted-generation).
 
 To enable assisted decoding, set the `assistant_model` argument with a model.
 
@@ -364,8 +363,6 @@ To enable assisted decoding, set the `assistant_model` argument with a model.
 When using assisted decoding with sampling methods, you can use the `temperarure` argument to control the randomness
 just like in multinomial sampling. However, in assisted decoding, reducing the temperature will help improving latency.
 
-<!-- TODO: link the blog post again to explain why the tradeoff exists -->
-
 ```python
 >>> from transformers import AutoModelForCausalLM, AutoTokenizer
 

docs/source/en/model_doc/pix2struct.mdx

@@ -25,6 +25,8 @@ Tips:
 Pix2Struct has been fine tuned on a variety of tasks and datasets, ranging from image captioning, visual question answering (VQA) over different inputs (books, charts, science diagrams), captioning UI components etc. The full list can be found in Table 1 of the paper.
 We therefore advise you to use these models for the tasks they have been fine tuned on. For instance, if you want to use Pix2Struct for UI captioning, you should use the model fine tuned on the UI dataset. If you want to use Pix2Struct for image captioning, you should use the model fine tuned on the natural images captioning dataset and so on.
 
+If you want to use the model to perform conditional text captioning, make sure to use the processor with `add_special_tokens=False`.
+
 This model was contributed by [ybelkada](https://huggingface.co/ybelkada).
 The original code can be found [here](https://github.com/google-research/pix2struct).
 

docs/source/ko/_toctree.yml

@@ -45,8 +45,8 @@
   - sections:
       - local: in_translation
         title: (번역중) Audio classification
-      - local: in_translation
-        title: (번역중) Automatic speech recognition
+      - local: tasks/asr
+        title: 자동 음성 인식
     title: (번역중) 오디오
     isExpanded: false
   - sections: