Merge branch 'master' into add_models_special_tokens_to_specific_configs

.circleci/config.yml

@@ -14,22 +14,6 @@ jobs:
             - run: sudo pip install codecov pytest-cov
             - run: python -m pytest -n 8 --dist=loadfile -s -v ./tests/ --cov
             - run: codecov
-    run_all_tests_torch_and_tf:
-        working_directory: ~/transformers
-        docker:
-            - image: circleci/python:3.5
-        environment:
-            OMP_NUM_THREADS: 1
-            RUN_SLOW: yes
-            RUN_CUSTOM_TOKENIZERS: yes
-        resource_class: xlarge
-        parallelism: 1
-        steps:
-            - checkout
-            - run: sudo pip install .[mecab,sklearn,tf-cpu,torch,testing]
-            - run:
-                command: python -m pytest -n 8 --dist=loadfile -s -v ./tests/
-                no_output_timeout: 4h
 
     run_tests_torch:
         working_directory: ~/transformers
@@ -134,13 +118,3 @@ workflows:
             - run_tests_torch
             - run_tests_tf
             - deploy_doc: *workflow_filters
-    run_slow_tests:
-        triggers:
-            - schedule:
-                cron: "0 4 * * *"
-                filters:
-                    branches:
-                        only:
-                            - master
-        jobs:
-            - run_all_tests_torch_and_tf

.github/workflows/github-push.yml

+name: GitHub-hosted runner
+
+on: push
+
+jobs:
+  check_code_quality:
+    runs-on: ubuntu-18.04
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v1
+      with:
+        python-version: 3.7
+    - name: Install dependencies
+      run: |
+        pip install .[tf,torch,quality]
+
+
+

.github/workflows/self-push.yml

+name: Self-hosted runner (push)
+
+on: 
+  push:
+    branches:
+      - master
+  pull_request:
+
+
+jobs:
+  run_tests_torch_and_tf_gpu:
+    runs-on: self-hosted
+    steps:
+    - uses: actions/checkout@v2
+    - name: Python version
+      run: |
+        which python
+        python --version
+        pip --version
+    - name: Current dir
+      run: pwd
+    - run: nvidia-smi
+    - name: Create new python env (on self-hosted runners we have to handle isolation ourselves)
+      run: |
+        python -m venv .env
+        source .env/bin/activate
+        which python
+        python --version
+        pip --version
+    - name: Install dependencies
+      run: |
+        source .env/bin/activate
+        pip install .[sklearn,tf,torch,testing]
+
+    - name: Are GPUs recognized by our DL frameworks
+      run: |
+        source .env/bin/activate
+        python -c "import torch; print(torch.cuda.is_available())"
+        python -c "import tensorflow as tf; print(tf.test.is_built_with_cuda(), tf.config.list_physical_devices('GPU'))"
+
+    - name: Run all non-slow tests on GPU
+      env:
+        TF_FORCE_GPU_ALLOW_GROWTH: "true"
+        # TF_GPU_MEMORY_LIMIT: 4096
+        OMP_NUM_THREADS: 1
+        USE_CUDA: yes
+      run: |
+        source .env/bin/activate
+        python -m pytest -n 2 --dist=loadfile -s -v ./tests/

.github/workflows/self-scheduled.yml

+name: Self-hosted runner (scheduled)
+
+on:
+  push:
+    branches:
+      - ci_*
+  repository_dispatch:
+  schedule:
+    - cron: "0 0 * * *"
+
+jobs:
+  run_all_tests_torch_and_tf_gpu:
+    runs-on: self-hosted
+    steps:
+    - uses: actions/checkout@v2
+    - name: Python version
+      run: |
+        which python
+        python --version
+        pip --version
+    - name: Current dir
+      run: pwd
+    - run: nvidia-smi
+    - name: Create new python env (on self-hosted runners we have to handle isolation ourselves)
+      run: |
+        python -m venv .env
+        source .env/bin/activate
+        which python
+        python --version
+        pip --version
+    - name: Install dependencies
+      run: |
+        source .env/bin/activate
+        pip install .[sklearn,tf,torch,testing]
+
+    - name: Are GPUs recognized by our DL frameworks
+      run: |
+        source .env/bin/activate
+        python -c "import torch; print(torch.cuda.is_available())"
+        python -c "import tensorflow as tf; print(tf.test.is_built_with_cuda(), tf.config.list_physical_devices('GPU'))"
+
+    - name: Run all tests on GPU
+      env:
+        TF_FORCE_GPU_ALLOW_GROWTH: "true"
+        OMP_NUM_THREADS: 1
+        RUN_SLOW: yes
+        USE_CUDA: yes
+      run: |
+        source .env/bin/activate
+        python -m pytest -n 1 --dist=loadfile -s -v ./tests/
+        

docker/Dockerfile

-FROM pytorch/pytorch:latest
-
-RUN git clone https://github.com/NVIDIA/apex.git && cd apex && python setup.py install --cuda_ext --cpp_ext
-
-RUN pip install transformers
-
-WORKDIR /workspace
\ No newline at end of file

docker/transformers-cpu/Dockerfile

+FROM ubuntu:18.04
+LABEL maintainer="Hugging Face"
+LABEL repository="transformers"
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+    jupyter \
+    tensorflow-cpu \
+    torch
+
+WORKDIR /workspace
+COPY . transformers/
+RUN cd transformers/ && \
+    python3 -m pip install --no-cache-dir .
+
+CMD ["/bin/bash"]
\ No newline at end of file

docker/transformers-gpu/Dockerfile

+FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04
+LABEL maintainer="Hugging Face"
+LABEL repository="transformers"
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+    jupyter \
+    tensorflow \
+    torch
+
+WORKDIR /workspace
+COPY . transformers/
+RUN cd transformers/ && \
+    python3 -m pip install --no-cache-dir .
+
+CMD ["/bin/bash"]
\ No newline at end of file

docker/transformers-pytorch-cpu/Dockerfile

+FROM ubuntu:18.04
+LABEL maintainer="Hugging Face"
+LABEL repository="transformers"
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+    jupyter \
+    torch
+
+WORKDIR /workspace
+COPY . transformers/
+RUN cd transformers/ && \
+    python3 -m pip install --no-cache-dir .
+
+CMD ["/bin/bash"]
\ No newline at end of file

docker/transformers-pytorch-gpu/Dockerfile

+FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04
+LABEL maintainer="Hugging Face"
+LABEL repository="transformers"
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+    mkl \
+    torch
+
+WORKDIR /workspace
+COPY . transformers/
+RUN cd transformers/ && \
+    python3 -m pip install --no-cache-dir .
+
+CMD ["/bin/bash"]
\ No newline at end of file

docker/transformers-tensorflow-cpu/Dockerfile

+FROM ubuntu:18.04
+LABEL maintainer="Hugging Face"
+LABEL repository="transformers"
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+    mkl \
+    tensorflow-cpu
+
+WORKDIR /workspace
+COPY . transformers/
+RUN cd transformers/ && \
+    python3 -m pip install --no-cache-dir .
+
+CMD ["/bin/bash"]
\ No newline at end of file

docker/transformers-tensorflow-gpu/Dockerfile

+FROM nvidia/cuda:10.1-cudnn7-runtime-ubuntu18.04
+LABEL maintainer="Hugging Face"
+LABEL repository="transformers"
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+    mkl \
+    tensorflow
+
+WORKDIR /workspace
+COPY . transformers/
+RUN cd transformers/ && \
+    python3 -m pip install --no-cache-dir .
+
+CMD ["/bin/bash"]
\ No newline at end of file

docs/source/_static/css/huggingface.css

+/* Our DOM objects */
+
+.framework-selector {
+    display: flex;
+    flex-direction: row;
+    justify-content: flex-end;
+}
+
+.framework-selector > button {
+    background-color: white;
+    color: #6670FF;
+    border: 1px solid #6670FF;
+    padding: 5px;
+}
+
+.framework-selector > button.selected{
+    background-color: #6670FF;
+    color: white;
+    border: 1px solid #6670FF;
+    padding: 5px;
+}
+
 /* The literal code blocks */
 .rst-content tt.literal, .rst-content tt.literal, .rst-content code.literal {
     color: #6670FF;

docs/source/_static/js/custom.js

@@ -68,6 +68,74 @@ function addHfMenu() {
     document.body.insertAdjacentHTML('afterbegin', div);
 }
 
+function platformToggle() {
+    const codeBlocks = Array.from(document.getElementsByClassName("highlight"));
+    const pytorchIdentifier = "## PYTORCH CODE";
+    const tensorflowIdentifier = "## TENSORFLOW CODE";
+    const pytorchSpanIdentifier = `<span class="c1">${pytorchIdentifier}</span>`;
+    const tensorflowSpanIdentifier = `<span class="c1">${tensorflowIdentifier}</span>`;
+
+    const getFrameworkSpans = filteredCodeBlock => {
+        const spans = filteredCodeBlock.element.innerHTML;
+        const pytorchSpanPosition = spans.indexOf(pytorchSpanIdentifier);
+        const tensorflowSpanPosition = spans.indexOf(tensorflowSpanIdentifier);
+
+        let pytorchSpans;
+        let tensorflowSpans;
+
+        if(pytorchSpanPosition < tensorflowSpanPosition){
+            pytorchSpans = spans.slice(pytorchSpanPosition + pytorchSpanIdentifier.length + 1, tensorflowSpanPosition);
+            tensorflowSpans = spans.slice(tensorflowSpanPosition + tensorflowSpanIdentifier.length + 1, spans.length);
+        }else{
+            tensorflowSpans = spans.slice(tensorflowSpanPosition + tensorflowSpanIdentifier.length + 1, pytorchSpanPosition);
+            pytorchSpans = spans.slice(pytorchSpanPosition + pytorchSpanIdentifier.length + 1, spans.length);
+        }
+
+        return {
+            ...filteredCodeBlock,
+            pytorchSample: pytorchSpans ,
+            tensorflowSample: tensorflowSpans
+        }
+    };
+
+    const createFrameworkButtons = sample => {
+            const pytorchButton = document.createElement("button");
+            pytorchButton.innerText = "PyTorch";
+
+            const tensorflowButton = document.createElement("button");
+            tensorflowButton.innerText = "TensorFlow";
+
+            const selectorDiv = document.createElement("div");
+            selectorDiv.classList.add("framework-selector");
+            selectorDiv.appendChild(pytorchButton);
+            selectorDiv.appendChild(tensorflowButton);
+            sample.element.parentElement.prepend(selectorDiv);
+
+            // Init on PyTorch
+            sample.element.innerHTML = sample.pytorchSample;
+            pytorchButton.classList.add("selected");
+            tensorflowButton.classList.remove("selected");
+
+            pytorchButton.addEventListener("click", () => {
+                sample.element.innerHTML = sample.pytorchSample;
+                pytorchButton.classList.add("selected");
+                tensorflowButton.classList.remove("selected");
+            });
+            tensorflowButton.addEventListener("click", () => {
+               sample.element.innerHTML = sample.tensorflowSample;
+                tensorflowButton.classList.add("selected");
+                pytorchButton.classList.remove("selected");
+            });
+        };
+
+    codeBlocks
+        .map(element => {return {element: element.firstChild, innerText: element.innerText}})
+        .filter(codeBlock => codeBlock.innerText.includes(pytorchIdentifier) && codeBlock.innerText.includes(tensorflowIdentifier))
+        .map(getFrameworkSpans)
+        .forEach(createFrameworkButtons);
+}
+
+
 /*!
  * github-buttons v2.2.10
  * (c) 2019 なつき
@@ -85,6 +153,7 @@ function onLoad() {
     addGithubButton();
     parseGithubButtons();
     addHfMenu();
+    platformToggle();
 }
 
 window.addEventListener("load", onLoad);

docs/source/_static/js/huggingface_logo.svg

-<svg width="95px" height="88px" viewBox="0 0 95 88" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-    <!-- Generator: Sketch 43.2 (39069) - http://www.bohemiancoding.com/sketch -->
+<svg clip-rule="evenodd" fill-rule="evenodd" stroke-linejoin="round" stroke-miterlimit="2" viewBox="0 0 127 118" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><clipPath id="a"><path clip-rule="nonzero" d="m62 75.052c13.105 0 17.333-11.684 17.333-17.684 0-3.118-2.096-2.136-5.453-.474-3.103 1.536-7.282 3.653-11.88 3.653-9.573 0-17.333-9.179-17.333-3.179s4.228 17.684 17.333 17.684z"/></clipPath><path d="m125.057 93.44c1 2.88.76 5.947-.573 8.613-.96 1.947-2.333 3.454-4.013 4.8-2.027 1.6-4.547 2.96-7.587 4.267-3.627 1.547-8.053 3-10.08 3.533-5.187 1.347-10.173 2.2-15.227 2.24-7.226.067-13.453-1.64-17.88-6-2.293.28-4.613.44-6.946.44-2.214 0-4.4-.133-6.574-.4-4.44 4.334-10.64 6.027-17.84 5.96-5.053-.04-10.04-.893-15.24-2.24-2.013-.533-6.44-1.986-10.066-3.533-3.04-1.307-5.56-2.667-7.574-4.267-1.693-1.346-3.066-2.853-4.026-4.8-1.32-2.666-1.574-5.733-.56-8.613-.934-2.2-1.174-4.72-.44-7.507.333-1.266.88-2.44 1.573-3.48-.147-.546-.267-1.106-.347-1.72-.506-3.653.76-6.986 3.147-9.573 1.173-1.293 2.44-2.187 3.76-2.76-.973-4.133-1.48-8.387-1.48-12.733 0-30.747 24.92-55.667 55.667-55.667 10.56 0 20.44 2.933 28.866 8.053 1.52.934 3.014 1.934 4.44 3 .707.534 1.414 1.08 2.094 1.654.693.56 1.373 1.146 2.026 1.746 1.974 1.8 3.827 3.734 5.52 5.8.574.68 1.12 1.387 1.654 2.107 1.08 1.427 2.08 2.907 3 4.44 1.4 2.293 2.626 4.693 3.693 7.187.707 1.666 1.32 3.373 1.867 5.12.813 2.613 1.44 5.306 1.866 8.08.134.92.254 1.853.347 2.786.187 1.867.293 3.76.293 5.694 0 4.293-.506 8.506-1.453 12.573 1.467.573 2.853 1.507 4.147 2.92 2.386 2.587 3.653 5.933 3.146 9.587-.08.6-.2 1.16-.346 1.706.693 1.04 1.24 2.214 1.573 3.48.733 2.787.493 5.307-.427 7.507" fill="#fff" fill-rule="nonzero"/><circle cx="62.333" cy="55.667" fill="#ffd21e" r="46.333"/><g fill-rule="nonzero"><path d="m108.667 55.667c0-25.59-20.744-46.334-46.334-46.334-25.589 0-46.333 20.744-46.333 46.334 0 25.589 20.744 46.333 46.333 46.333 25.59 0 46.334-20.744 46.334-46.333zm-98 0c0-28.535 23.132-51.667 51.666-51.667 28.535 0 51.667 23.132 51.667 51.667 0 28.534-23.132 51.666-51.667 51.666-28.534 0-51.666-23.132-51.666-51.666z" fill="#ffac03"/><path d="m77.387 43.055c1.7.6 2.376 4.093 4.092 3.181 3.251-1.729 4.485-5.765 2.757-9.016-1.729-3.251-5.765-4.485-9.016-2.757-3.251 1.729-4.485 5.765-2.757 9.016.816 1.535 3.406-.96 4.924-.424z" fill="#3a3b45"/><path d="m45.978 43.055c-1.699.6-2.375 4.093-4.092 3.181-3.251-1.729-4.485-5.765-2.756-9.016 1.728-3.251 5.765-4.485 9.016-2.757 3.251 1.729 4.485 5.765 2.756 9.016-.815 1.535-3.405-.96-4.924-.424z" fill="#3a3b45"/><path d="m62 75.052c13.105 0 17.333-11.684 17.333-17.684 0-3.118-2.096-2.136-5.453-.474-3.103 1.536-7.282 3.653-11.88 3.653-9.573 0-17.333-9.179-17.333-3.179s4.228 17.684 17.333 17.684z" fill="#3a3b45"/></g><g clip-path="url(#a)"><path d="m62.333 88.667c6.387 0 11.564-5.178 11.564-11.564 0-4.975-3.141-9.216-7.548-10.848-.162-.06-.326-.116-.491-.169-1.111-.355-2.296 3.464-3.525 3.464-1.148 0-2.257-3.844-3.305-3.532-4.776 1.422-8.259 5.847-8.259 11.085 0 6.386 5.178 11.564 11.564 11.564z" fill="#ef4e4e" fill-rule="nonzero"/></g><circle cx="93.667" cy="45" fill="#ffd21e" r="4.333"/><circle cx="31.667" cy="45" fill="#ffd21e" r="4.333"/><path d="m22.749 64c-2.158 0-4.088.887-5.433 2.495-.832.996-1.701 2.601-1.772 5.005-.905-.26-1.776-.405-2.589-.405-2.067 0-3.934.792-5.254 2.23-1.696 1.847-2.449 4.116-2.121 6.387.156 1.081.517 2.051 1.057 2.948-1.138.921-1.977 2.204-2.382 3.747-.318 1.209-.643 3.728 1.056 6.322-.108.17-.21.346-.304.526-1.022 1.938-1.087 4.129-.186 6.169 1.367 3.092 4.763 5.528 11.358 8.143 4.102 1.626 7.856 2.666 7.889 2.676 5.424 1.406 10.329 2.121 14.576 2.121 7.805 0 13.393-2.391 16.609-7.105 5.176-7.592 4.436-14.536-2.261-21.23-3.707-3.704-6.171-9.165-6.684-10.364-1.035-3.549-3.771-7.494-8.319-7.494h-.001c-.383 0-.769.03-1.151.09-1.992.314-3.733 1.46-4.977 3.186-1.343-1.67-2.647-2.998-3.827-3.747-1.778-1.128-3.556-1.7-5.284-1.7m0 5.333c.68 0 1.511.29 2.427.871 2.844 1.804 8.332 11.237 10.341 14.907.674 1.229 1.824 1.749 2.86 1.749 2.056 0 3.662-2.044.188-4.641-5.222-3.908-3.39-10.296-.897-10.69.109-.017.217-.025.321-.025 2.267 0 3.267 3.907 3.267 3.907s2.931 7.36 7.965 12.39c5.035 5.032 5.295 9.071 1.626 14.452-2.503 3.67-7.294 4.778-12.203 4.778-5.092 0-10.312-1.192-13.237-1.951-.144-.037-17.935-5.063-15.682-9.34.379-.719 1.003-1.007 1.788-1.007 3.174 0 8.946 4.723 11.427 4.723.555 0 .945-.236 1.105-.812 1.058-3.793-16.076-5.388-14.632-10.883.255-.972.946-1.366 1.916-1.365 4.194 0 13.602 7.375 15.574 7.375.15 0 .258-.044.317-.138.988-1.594.447-2.708-6.517-6.922-6.964-4.216-11.852-6.752-9.072-9.779.32-.349.773-.504 1.324-.504 4.228.001 14.217 9.092 14.217 9.092s2.696 2.804 4.327 2.804c.374 0 .693-.148.909-.513 1.156-1.95-10.737-10.963-11.408-14.682-.455-2.52.319-3.796 1.749-3.796" fill="#ffac03" fill-rule="nonzero"/><path d="m50.846 102.253c3.67-5.381 3.41-9.42-1.625-14.452-5.035-5.03-7.965-12.39-7.965-12.39s-1.095-4.275-3.588-3.882c-2.494.394-4.324 6.782.898 10.69 5.223 3.906-1.04 6.561-3.049 2.892-2.009-3.67-7.496-13.103-10.341-14.907-2.844-1.804-4.847-.793-4.176 2.925.67 3.719 12.565 12.732 11.408 14.683-1.158 1.949-5.236-2.292-5.236-2.292s-12.763-11.615-15.542-8.588c-2.778 3.027 2.108 5.563 9.072 9.779 6.966 4.214 7.506 5.328 6.518 6.922-.99 1.595-16.363-11.366-17.807-5.872-1.443 5.495 15.689 7.09 14.632 10.883-1.057 3.795-12.068-7.18-14.32-2.904-2.253 4.277 15.537 9.303 15.681 9.34 5.747 1.491 20.342 4.649 25.44-2.827" fill="#ffd21e" fill-rule="nonzero"/><path d="m102.584 64c2.159 0 4.088.887 5.433 2.495.832.996 1.702 2.601 1.772 5.005.906-.26 1.776-.405 2.59-.405 2.066 0 3.933.792 5.253 2.23 1.696 1.847 2.449 4.116 2.121 6.387-.156 1.081-.517 2.051-1.057 2.948 1.139.921 1.977 2.204 2.383 3.747.317 1.209.642 3.728-1.056 6.322.108.17.209.346.304.526 1.021 1.938 1.086 4.129.185 6.169-1.367 3.092-4.763 5.528-11.357 8.143-4.103 1.626-7.856 2.666-7.89 2.676-5.424 1.406-10.329 2.121-14.576 2.121-7.805 0-13.393-2.391-16.609-7.105-5.176-7.592-4.436-14.536 2.261-21.23 3.707-3.704 6.171-9.165 6.684-10.364 1.035-3.549 3.771-7.494 8.319-7.494h.001c.383 0 .77.03 1.151.09 1.992.314 3.733 1.46 4.977 3.186 1.343-1.67 2.647-2.998 3.827-3.747 1.779-1.128 3.556-1.7 5.284-1.7m0 5.333c-.68 0-1.511.29-2.427.871-2.844 1.804-8.332 11.237-10.341 14.907-.673 1.229-1.824 1.749-2.86 1.749-2.056 0-3.661-2.044-.188-4.641 5.223-3.908 3.391-10.296.897-10.69-.109-.017-.217-.025-.321-.025-2.267 0-3.267 3.907-3.267 3.907s-2.93 7.36-7.965 12.39c-5.035 5.032-5.295 9.071-1.625 14.452 2.502 3.67 7.293 4.778 12.202 4.778 5.092 0 10.312-1.192 13.238-1.951.144-.037 17.934-5.063 15.681-9.34-.379-.719-1.003-1.007-1.788-1.007-3.173 0-8.945 4.723-11.427 4.723-.554 0-.945-.236-1.105-.812-1.057-3.793 16.076-5.388 14.632-10.883-.255-.972-.945-1.366-1.916-1.365-4.193 0-13.601 7.375-15.573 7.375-.151 0-.259-.044-.318-.138-.988-1.594-.446-2.708 6.518-6.922 6.964-4.216 11.852-6.752 9.072-9.779-.32-.349-.774-.504-1.324-.504-4.228.001-14.218 9.092-14.218 9.092s-2.696 2.804-4.326 2.804c-.375 0-.694-.148-.91-.513-1.156-1.95 10.738-10.963 11.408-14.682.455-2.52-.318-3.796-1.749-3.796" fill="#ffac03" fill-rule="nonzero"/><path d="m74.487 102.253c-3.669-5.381-3.409-9.42 1.625-14.452 5.035-5.03 7.966-12.39 7.966-12.39s1.094-4.275 3.588-3.882c2.493.394 4.324 6.782-.899 10.69-5.223 3.906 1.04 6.561 3.049 2.892 2.01-3.67 7.496-13.103 10.342-14.907 2.844-1.804 4.846-.793 4.176 2.925-.671 3.719-12.566 12.732-11.408 14.683 1.157 1.949 5.236-2.292 5.236-2.292s12.762-11.615 15.541-8.588-2.108 5.563-9.072 9.779c-6.965 4.214-7.505 5.328-6.517 6.922.989 1.595 16.362-11.366 17.806-5.872 1.443 5.495-15.689 7.09-14.632 10.883 1.058 3.795 12.068-7.18 14.32-2.904 2.254 4.277-15.537 9.303-15.681 9.34-5.747 1.491-20.341 4.649-25.44-2.827" fill="#ffd21e" fill-rule="nonzero"/></svg>
\ No newline at end of file
-    <title>icon</title>
-    <desc>Created with Sketch.</desc>
-    <defs>
-        <path d="M13,14.7890193 C22.8284801,14.7890193 26,6.02605902 26,1.5261751 C26,-0.812484109 24.4279133,-0.0763570998 21.9099482,1.17020987 C19.5830216,2.32219957 16.4482998,3.91011313 13,3.91011313 C5.82029825,3.91011313 0,-2.97370882 0,1.5261751 C0,6.02605902 3.17151989,14.7890193 13,14.7890193 Z" id="path-1"></path>
-    </defs>
-    <g id="Page-1" stroke="none" stroke-width="1" fill="none" fill-rule="evenodd">
-        <g id="icon_desktop">
-            <g id="icon">
-                <g id="icon_desktop">
-                    <g id="Group-2">
-                        <g id="Group">
-                            <path d="M93.7930402,70.08 C94.5430402,72.24 94.3630402,74.54 93.3630402,76.54 C92.6430402,78 91.6130402,79.13 90.3530402,80.14 C88.8330402,81.34 86.9430402,82.36 84.6630402,83.34 C81.9430402,84.5 78.6230402,85.59 77.1030402,85.99 C73.2130402,87 69.4730402,87.64 65.6830402,87.67 C60.2630402,87.72 55.5930402,86.44 52.2730402,83.17 C50.5530402,83.38 48.8130402,83.5 47.0630402,83.5 C45.4030402,83.5 43.7630402,83.4 42.1330402,83.2 C38.8030402,86.45 34.1530402,87.72 28.7530402,87.67 C24.9630402,87.64 21.2230402,87 17.3230402,85.99 C15.8130402,85.59 12.4930402,84.5 9.77304019,83.34 C7.49304019,82.36 5.60304019,81.34 4.09304019,80.14 C2.82304019,79.13 1.79304019,78 1.07304019,76.54 C0.0830401858,74.54 -0.106959814,72.24 0.653040186,70.08 C-0.0469598142,68.43 -0.226959814,66.54 0.323040186,64.45 C0.573040186,63.5 0.983040186,62.62 1.50304019,61.84 C1.39304019,61.43 1.30304019,61.01 1.24304019,60.55 C0.863040186,57.81 1.81304019,55.31 3.60304019,53.37 C4.48304019,52.4 5.43304019,51.73 6.42304019,51.3 C5.69304019,48.2 5.31304019,45.01 5.31304019,41.75 C5.31304019,18.69 24.0030402,0 47.0630402,0 C54.9830402,0 62.3930402,2.2 68.7130402,6.04 C69.8530402,6.74 70.9730402,7.49 72.0430402,8.29 C72.5730402,8.69 73.1030402,9.1 73.6130402,9.53 C74.1330402,9.95 74.6430402,10.39 75.1330402,10.84 C76.6130402,12.19 78.0030402,13.64 79.2730402,15.19 C79.7030402,15.7 80.1130402,16.23 80.5130402,16.77 C81.3230402,17.84 82.0730402,18.95 82.7630402,20.1 C83.8130402,21.82 84.7330402,23.62 85.5330402,25.49 C86.0630402,26.74 86.5230402,28.02 86.9330402,29.33 C87.5430402,31.29 88.0130402,33.31 88.3330402,35.39 C88.4330402,36.08 88.5230402,36.78 88.5930402,37.48 C88.7330402,38.88 88.8130402,40.3 88.8130402,41.75 C88.8130402,44.97 88.4330402,48.13 87.7230402,51.18 C88.8230402,51.61 89.8630402,52.31 90.8330402,53.37 C92.6230402,55.31 93.5730402,57.82 93.1930402,60.56 C93.1330402,61.01 93.0430402,61.43 92.9330402,61.84 C93.4530402,62.62 93.8630402,63.5 94.1130402,64.45 C94.6630402,66.54 94.4830402,68.43 93.7930402,70.08" id="Fill-1" fill="#FFFFFF" fill-rule="nonzero"></path>
-                            <circle id="Oval" fill="#FFD21E" fill-rule="nonzero" cx="46.75" cy="41.75" r="34.75"></circle>
-                            <path d="M81.5,41.75 C81.5,22.5581049 65.9418951,7 46.75,7 C27.5581049,7 12,22.5581049 12,41.75 C12,60.9418951 27.5581049,76.5 46.75,76.5 C65.9418951,76.5 81.5,60.9418951 81.5,41.75 Z M8,41.75 C8,20.3489659 25.3489659,3 46.75,3 C68.1510341,3 85.5,20.3489659 85.5,41.75 C85.5,63.1510341 68.1510341,80.5 46.75,80.5 C25.3489659,80.5 8,63.1510341 8,41.75 Z" id="Oval" fill="#FFAC03" fill-rule="nonzero"></path>
-                            <path d="M57.1723547,31.7151181 C58.0863134,32.7107502 57.3040427,35.2620959 58.7620957,35.2620959 C61.5235194,35.2620959 63.7620957,33.0235196 63.7620957,30.2620959 C63.7620957,27.5006721 61.5235194,25.2620959 58.7620957,25.2620959 C56.0006719,25.2620959 53.7620957,27.5006721 53.7620957,30.2620959 C53.7620957,31.5654666 56.3553563,30.8251108 57.1723547,31.7151181 Z" id="Oval-2" fill="#3A3B45" fill-rule="nonzero" transform="translate(58.762096, 30.262096) rotate(-28.000000) translate(-58.762096, -30.262096) "></path>
-                            <path d="M32.1723553,31.7151181 C33.086314,32.7107502 32.3040433,35.2620959 33.7620963,35.2620959 C36.52352,35.2620959 38.7620963,33.0235196 38.7620963,30.2620959 C38.7620963,27.5006721 36.52352,25.2620959 33.7620963,25.2620959 C31.0006725,25.2620959 28.7620963,27.5006721 28.7620963,30.2620959 C28.7620963,31.5654666 31.3553569,30.8251108 32.1723553,31.7151181 Z" id="Oval-2" fill="#3A3B45" fill-rule="nonzero" transform="translate(33.762096, 30.262096) scale(-1, 1) rotate(-28.000000) translate(-33.762096, -30.262096) "></path>
-                            <g id="Oval-4" transform="translate(33.500000, 41.500000)">
-                                <g id="Mask" fill-rule="nonzero" fill="#3A3B45">
-                                    <path d="M13,14.7890193 C22.8284801,14.7890193 26,6.02605902 26,1.5261751 C26,-0.812484109 24.4279133,-0.0763570998 21.9099482,1.17020987 C19.5830216,2.32219957 16.4482998,3.91011313 13,3.91011313 C5.82029825,3.91011313 0,-2.97370882 0,1.5261751 C0,6.02605902 3.17151989,14.7890193 13,14.7890193 Z" id="path-1"></path>
-                                </g>
-                                <g id="Clipped">
-                                    <mask id="mask-2" fill="white">
-                                        <use xlink:href="#path-1"></use>
-                                    </mask>
-                                    <g id="path-1"></g>
-                                    <path d="M13.25,25 C18.0399291,25 21.9229338,21.1169953 21.9229338,16.3270662 C21.9229338,12.5962324 19.5672252,9.41560375 16.2620987,8.19147116 C16.1404592,8.14641904 16.0175337,8.10401696 15.8933923,8.06433503 C15.0599892,7.79793679 14.1717882,10.6623144 13.25,10.6623144 C12.3886883,10.6623144 11.5567012,7.77968641 10.7713426,8.01349068 C7.18916268,9.07991937 4.57706621,12.3984489 4.57706621,16.3270662 C4.57706621,21.1169953 8.46007093,25 13.25,25 Z" id="Shape" fill="#EF4E4E" fill-rule="nonzero" mask="url(#mask-2)"></path>
-                                </g>
-                            </g>
-                            <circle id="Oval-3" fill="#FFD21E" fill-rule="nonzero" style="mix-blend-mode: multiply;" cx="70.25" cy="33.75" r="3.25"></circle>
-                            <circle id="Oval-3" fill="#FFD21E" fill-rule="nonzero" style="mix-blend-mode: multiply;" cx="23.75" cy="33.75" r="3.25"></circle>
-                        </g>
-                    </g>
-                </g>
-                <g id="Group-4" transform="translate(3.000000, 48.000000)" fill-rule="nonzero">
-                    <path d="M14.0619453,0 L14.0619453,0 C12.4429453,0 10.9959453,0.665 9.98694534,1.871 C9.36294534,2.618 8.71094534,3.822 8.65794534,5.625 C7.97894534,5.43 7.32594534,5.321 6.71594534,5.321 C5.16594534,5.321 3.76594534,5.915 2.77594534,6.994 C1.50394534,8.379 0.938945345,10.081 1.18494534,11.784 C1.30194534,12.595 1.57294534,13.322 1.97794534,13.995 C1.12394534,14.686 0.494945345,15.648 0.190945345,16.805 C-0.0470546551,17.712 -0.291054655,19.601 0.982945345,21.547 C0.901945345,21.674 0.825945345,21.806 0.754945345,21.941 C-0.0110546551,23.395 -0.0600546551,25.038 0.615945345,26.568 C1.64094534,28.887 4.18794534,30.714 9.13394534,32.675 C12.2109453,33.895 15.0259453,34.675 15.0509453,34.682 C19.1189453,35.737 22.7979453,36.273 25.9829453,36.273 C31.8369453,36.273 36.0279453,34.48 38.4399453,30.944 C42.3219453,25.25 41.7669453,20.042 36.7439453,15.022 C33.9639453,12.244 32.1159453,8.148 31.7309453,7.249 C30.9549453,4.587 28.9029453,1.628 25.4919453,1.628 L25.4909453,1.628 C25.2039453,1.628 24.9139453,1.651 24.6279453,1.696 C23.1339453,1.931 21.8279453,2.791 20.8949453,4.085 C19.8879453,2.833 18.9099453,1.837 18.0249453,1.275 C16.6909453,0.429 15.3579453,0 14.0619453,0 M14.0619453,4 C14.5719453,4 15.1949453,4.217 15.8819453,4.653 C18.0149453,6.006 22.1309453,13.081 23.6379453,15.833 C24.1429453,16.755 25.0059453,17.145 25.7829453,17.145 C27.3249453,17.145 28.5289453,15.612 25.9239453,13.664 C22.0069453,10.733 23.3809453,5.942 25.2509453,5.647 C25.3329453,5.634 25.4139453,5.628 25.4919453,5.628 C27.1919453,5.628 27.9419453,8.558 27.9419453,8.558 C27.9419453,8.558 30.1399453,14.078 33.9159453,17.851 C37.6919453,21.625 37.8869453,24.654 35.1349453,28.69 C33.2579453,31.442 29.6649453,32.273 25.9829453,32.273 C22.1639453,32.273 18.2489453,31.379 16.0549453,30.81 C15.9469453,30.782 2.60394534,27.013 4.29394534,23.805 C4.57794534,23.266 5.04594534,23.05 5.63494534,23.05 C8.01494534,23.05 12.3439453,26.592 14.2049453,26.592 C14.6209453,26.592 14.9139453,26.415 15.0339453,25.983 C15.8269453,23.138 2.97694534,21.942 4.05994534,17.821 C4.25094534,17.092 4.76894534,16.796 5.49694534,16.797 C8.64194534,16.797 15.6979453,22.328 17.1769453,22.328 C17.2899453,22.328 17.3709453,22.295 17.4149453,22.225 C18.1559453,21.029 17.7499453,20.194 12.5269453,17.033 C7.30394534,13.871 3.63794534,11.969 5.72294534,9.699 C5.96294534,9.437 6.30294534,9.321 6.71594534,9.321 C9.88694534,9.322 17.3789453,16.14 17.3789453,16.14 C17.3789453,16.14 19.4009453,18.243 20.6239453,18.243 C20.9049453,18.243 21.1439453,18.132 21.3059453,17.858 C22.1729453,16.396 13.2529453,9.636 12.7499453,6.847 C12.4089453,4.957 12.9889453,4 14.0619453,4" id="Fill-1" fill="#FFAC03"></path>
-                    <path d="M35.1348,28.6899 C37.8868,24.6539 37.6918,21.6249 33.9158,17.8509 C30.1398,14.0779 27.9418,8.5579 27.9418,8.5579 C27.9418,8.5579 27.1208,5.3519 25.2508,5.6469 C23.3808,5.9419 22.0078,10.7329 25.9248,13.6639 C29.8418,16.5939 25.1448,18.5849 23.6378,15.8329 C22.1308,13.0809 18.0158,6.0059 15.8818,4.6529 C13.7488,3.2999 12.2468,4.0579 12.7498,6.8469 C13.2528,9.6359 22.1738,16.3959 21.3058,17.8589 C20.4378,19.3209 17.3788,16.1399 17.3788,16.1399 C17.3788,16.1399 7.8068,7.4289 5.7228,9.6989 C3.6388,11.9689 7.3038,13.8709 12.5268,17.0329 C17.7508,20.1939 18.1558,21.0289 17.4148,22.2249 C16.6728,23.4209 5.1428,13.6999 4.0598,17.8209 C2.9778,21.9419 15.8268,23.1379 15.0338,25.9829 C14.2408,28.8289 5.9828,20.5979 4.2938,23.8049 C2.6038,27.0129 15.9468,30.7819 16.0548,30.8099 C20.3648,31.9279 31.3108,34.2969 35.1348,28.6899" id="Fill-4" fill="#FFD21E"></path>
-                </g>
-                <g id="Group-4" transform="translate(70.500000, 66.500000) scale(-1, 1) translate(-70.500000, -66.500000) translate(50.000000, 48.000000)" fill-rule="nonzero">
-                    <path d="M14.0619453,0 L14.0619453,0 C12.4429453,0 10.9959453,0.665 9.98694534,1.871 C9.36294534,2.618 8.71094534,3.822 8.65794534,5.625 C7.97894534,5.43 7.32594534,5.321 6.71594534,5.321 C5.16594534,5.321 3.76594534,5.915 2.77594534,6.994 C1.50394534,8.379 0.938945345,10.081 1.18494534,11.784 C1.30194534,12.595 1.57294534,13.322 1.97794534,13.995 C1.12394534,14.686 0.494945345,15.648 0.190945345,16.805 C-0.0470546551,17.712 -0.291054655,19.601 0.982945345,21.547 C0.901945345,21.674 0.825945345,21.806 0.754945345,21.941 C-0.0110546551,23.395 -0.0600546551,25.038 0.615945345,26.568 C1.64094534,28.887 4.18794534,30.714 9.13394534,32.675 C12.2109453,33.895 15.0259453,34.675 15.0509453,34.682 C19.1189453,35.737 22.7979453,36.273 25.9829453,36.273 C31.8369453,36.273 36.0279453,34.48 38.4399453,30.944 C42.3219453,25.25 41.7669453,20.042 36.7439453,15.022 C33.9639453,12.244 32.1159453,8.148 31.7309453,7.249 C30.9549453,4.587 28.9029453,1.628 25.4919453,1.628 L25.4909453,1.628 C25.2039453,1.628 24.9139453,1.651 24.6279453,1.696 C23.1339453,1.931 21.8279453,2.791 20.8949453,4.085 C19.8879453,2.833 18.9099453,1.837 18.0249453,1.275 C16.6909453,0.429 15.3579453,0 14.0619453,0 M14.0619453,4 C14.5719453,4 15.1949453,4.217 15.8819453,4.653 C18.0149453,6.006 22.1309453,13.081 23.6379453,15.833 C24.1429453,16.755 25.0059453,17.145 25.7829453,17.145 C27.3249453,17.145 28.5289453,15.612 25.9239453,13.664 C22.0069453,10.733 23.3809453,5.942 25.2509453,5.647 C25.3329453,5.634 25.4139453,5.628 25.4919453,5.628 C27.1919453,5.628 27.9419453,8.558 27.9419453,8.558 C27.9419453,8.558 30.1399453,14.078 33.9159453,17.851 C37.6919453,21.625 37.8869453,24.654 35.1349453,28.69 C33.2579453,31.442 29.6649453,32.273 25.9829453,32.273 C22.1639453,32.273 18.2489453,31.379 16.0549453,30.81 C15.9469453,30.782 2.60394534,27.013 4.29394534,23.805 C4.57794534,23.266 5.04594534,23.05 5.63494534,23.05 C8.01494534,23.05 12.3439453,26.592 14.2049453,26.592 C14.6209453,26.592 14.9139453,26.415 15.0339453,25.983 C15.8269453,23.138 2.97694534,21.942 4.05994534,17.821 C4.25094534,17.092 4.76894534,16.796 5.49694534,16.797 C8.64194534,16.797 15.6979453,22.328 17.1769453,22.328 C17.2899453,22.328 17.3709453,22.295 17.4149453,22.225 C18.1559453,21.029 17.7499453,20.194 12.5269453,17.033 C7.30394534,13.871 3.63794534,11.969 5.72294534,9.699 C5.96294534,9.437 6.30294534,9.321 6.71594534,9.321 C9.88694534,9.322 17.3789453,16.14 17.3789453,16.14 C17.3789453,16.14 19.4009453,18.243 20.6239453,18.243 C20.9049453,18.243 21.1439453,18.132 21.3059453,17.858 C22.1729453,16.396 13.2529453,9.636 12.7499453,6.847 C12.4089453,4.957 12.9889453,4 14.0619453,4" id="Fill-1" fill="#FFAC03"></path>
-                    <path d="M35.1348,28.6899 C37.8868,24.6539 37.6918,21.6249 33.9158,17.8509 C30.1398,14.0779 27.9418,8.5579 27.9418,8.5579 C27.9418,8.5579 27.1208,5.3519 25.2508,5.6469 C23.3808,5.9419 22.0078,10.7329 25.9248,13.6639 C29.8418,16.5939 25.1448,18.5849 23.6378,15.8329 C22.1308,13.0809 18.0158,6.0059 15.8818,4.6529 C13.7488,3.2999 12.2468,4.0579 12.7498,6.8469 C13.2528,9.6359 22.1738,16.3959 21.3058,17.8589 C20.4378,19.3209 17.3788,16.1399 17.3788,16.1399 C17.3788,16.1399 7.8068,7.4289 5.7228,9.6989 C3.6388,11.9689 7.3038,13.8709 12.5268,17.0329 C17.7508,20.1939 18.1558,21.0289 17.4148,22.2249 C16.6728,23.4209 5.1428,13.6999 4.0598,17.8209 C2.9778,21.9419 15.8268,23.1379 15.0338,25.9829 C14.2408,28.8289 5.9828,20.5979 4.2938,23.8049 C2.6038,27.0129 15.9468,30.7819 16.0548,30.8099 C20.3648,31.9279 31.3108,34.2969 35.1348,28.6899" id="Fill-4" fill="#FFD21E"></path>
-                </g>
-            </g>
-        </g>
-    </g>
-</svg>
\ No newline at end of file

docs/source/conf.py

@@ -20,7 +20,7 @@ sys.path.insert(0, os.path.abspath('../../src'))
 # -- Project information -----------------------------------------------------
 
 project = u'transformers'
-copyright = u'2019, huggingface'
+copyright = u'2020, huggingface'
 author = u'huggingface'
 
 # The short X.Y version
@@ -105,6 +105,12 @@ html_static_path = ['_static']
 #
 # html_sidebars = {}
 
+# This must be the name of an image file (path relative to the configuration 
+# directory) that is the favicon of the docs. Modern browsers use this as 
+# the icon for tabs, windows and bookmarks. It should be a Windows-style 
+# icon file (.ico).
+html_favicon = 'favicon.ico'
+
 
 # -- Options for HTMLHelp output ---------------------------------------------
 

docs/source/index.rst

@@ -61,6 +61,7 @@ The library currently contains PyTorch and Tensorflow implementations, pre-train
     quickstart
     glossary
     pretrained_models
+    usage
     model_sharing
     examples
     notebooks
@@ -79,6 +80,7 @@ The library currently contains PyTorch and Tensorflow implementations, pre-train
     main_classes/configuration
     main_classes/model
     main_classes/tokenizer
+    main_classes/pipelines
     main_classes/optimizer_schedules
     main_classes/processors
 

docs/source/main_classes/pipelines.rst

+Pipelines
+----------------------------------------------------
+
+The pipelines are a great and easy way to use models for inference. These pipelines are objects that abstract most
+of the complex code from the library, offering a simple API dedicated to several tasks, including Named Entity
+Recognition, Masked Language Modeling, Sentiment Analysis, Feature Extraction and Question Answering.
+
+There are two categories of pipeline abstractions to be aware about:
+
+- The :class:`~transformers.pipeline` which is the most powerful object encapsulating all other pipelines
+- The other task-specific pipelines, such as :class:`~transformers.NerPipeline`
+  or :class:`~transformers.QuestionAnsweringPipeline`
+
+The pipeline abstraction
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The `pipeline` abstraction is a wrapper around all the other available pipelines. It is instantiated as any
+other pipeline but requires an additional argument which is the `task`.
+
+.. autoclass:: transformers.pipeline
+    :members:
+
+
+The task specific pipelines
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Parent class: Pipeline
+=========================================
+
+.. autoclass:: transformers.Pipeline
+    :members: predict, transform, save_pretrained
+
+NerPipeline
+==========================================
+
+.. autoclass:: transformers.NerPipeline
+
+TokenClassificationPipeline
+==========================================
+
+This class is an alias of the :class:`~transformers.NerPipeline` defined above. Please refer to that pipeline for
+documentation and usage examples.
+
+FillMaskPipeline
+==========================================
+
+.. autoclass:: transformers.FillMaskPipeline
+
+FeatureExtractionPipeline
+==========================================
+
+.. autoclass:: transformers.FeatureExtractionPipeline
+
+TextClassificationPipeline
+==========================================
+
+.. autoclass:: transformers.TextClassificationPipeline
+
+QuestionAnsweringPipeline
+==========================================
+
+.. autoclass:: transformers.QuestionAnsweringPipeline
+

docs/source/model_doc/albert.rst

@@ -41,7 +41,8 @@ AlbertTokenizer
 ~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.AlbertTokenizer
-    :members:
+    :members: build_inputs_with_special_tokens, get_special_tokens_mask,
+        create_token_type_ids_from_sequences, save_vocabulary
 
 
 AlbertModel

docs/source/model_doc/bart.rst

@@ -4,20 +4,27 @@ Bart
 file a `Github Issue <https://github.com/huggingface/transformers/issues/new?assignees=&labels=&template=bug-report.md&title>`__ and assign
 @sshleifer
 
-The Bart model was `proposed <https://arxiv.org/abs/1910.13461>`_ by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer on 29 Oct, 2019.
-It is a sequence to sequence model where both encoder and decoder are transformers. The paper also introduces a novel pretraining objective, and demonstrates excellent summarization results.
-The authors released their code `here <https://github.com/pytorch/fairseq/tree/master/examples/bart>`_
+Paper
+~~~~~
+The Bart model was `proposed <https://arxiv.org/abs/1910.13461>`_ by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer on 29 Oct, 2019.
+According to the abstract:
 
-**Abstract:**
+- Bart uses a standard seq2seq/machine translation architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT).
+- The pretraining task involves randomly shuffling the order of the original sentences and a novel in-filling scheme, where spans of text are replaced with a single mask token.
+- BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE.
 
-*We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Tranformer-based neural machine translation architecture which, despite its simplicity, can be seen as generalizing BERT (due to the bidirectional encoder), GPT (with the left-to-right decoder), and many other more recent pretraining schemes. We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token. BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa with comparable training resources on GLUE and SQuAD, achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 6 ROUGE. BART also provides a 1.1 BLEU increase over a back-translation system for machine translation, with only target language pretraining. We also report ablation experiments that replicate other pretraining schemes within the BART framework, to better measure which factors most influence end-task performance.*
-`BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension`
+The Authors' code can be found `here <https://github.com/pytorch/fairseq/tree/master/examples/bart>`_
 
 
-Notes:
+Implementation Notes
+~~~~~~~~~~~~~~~~~~~~
 - Bart doesn't use :obj:`token_type_ids`, for sequence classification just use BartTokenizer.encode to get the proper splitting.
 - Inputs to the decoder are created by BartModel.forward if they are not passed. This is different than some other model APIs.
 - Model predictions are intended to be identical to the original implementation. This only works, however, if the string you pass to fairseq.encode starts with a space.
+- Decoder inputs are created automatically by the helper function ``transformers.modeling_bart._prepare_bart_decoder_inputs``
+BartModel
+- ``MaskedLM.generate`` should be used for summarization, see the example in that docstrings
+
 
 BartModel
 ~~~~~~~~~~~~~~~~~~~~
@@ -30,7 +37,7 @@ BartForMaskedLM
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. autoclass:: transformers.BartForMaskedLM
-    :members: forward
+    :members: forward, generate
 
 
 BartForSequenceClassification