shoarora · shoarora · Mar 30, 2020 · Mar 8, 2020 · Mar 8, 2020 · Mar 8, 2020
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -3,7 +3,7 @@ jobs:
     run_tests_torch_and_tf:
         working_directory: ~/transformers
         docker:
-            - image: circleci/python:3.5
+            - image: circleci/python:3.6
         environment:
             OMP_NUM_THREADS: 1
         resource_class: xlarge
@@ -46,7 +46,7 @@ jobs:
     run_tests_custom_tokenizers:
         working_directory: ~/transformers
         docker:
-            - image: circleci/python:3.5
+            - image: circleci/python:3.6
         environment:
             RUN_CUSTOM_TOKENIZERS: yes
         steps:
@@ -56,7 +56,7 @@ jobs:
     run_examples_torch:
         working_directory: ~/transformers
         docker:
-            - image: circleci/python:3.5
+            - image: circleci/python:3.6
         environment:
             OMP_NUM_THREADS: 1
         resource_class: xlarge
@@ -69,7 +69,7 @@ jobs:
     deploy_doc:
         working_directory: ~/transformers
         docker:
-            - image: circleci/python:3.5
+            - image: circleci/python:3.6
         steps:
             - add_ssh_keys:
                 fingerprints:
@@ -94,7 +94,7 @@ jobs:
     check_repository_consistency:
         working_directory: ~/transformers
         docker:
-            - image: circleci/python:3.5
+            - image: circleci/python:3.6
         resource_class: small
         parallelism: 1
         steps:

diff --git a/.github/workflows/self-push.yml b/.github/workflows/self-push.yml
@@ -1,10 +1,11 @@
 name: Self-hosted runner (push)
 
 on: 
-  push:
-    branches:
-      - master
-  pull_request:
+  # push:
+  #   branches:
+  #     - master
+  # pull_request:
+  repository_dispatch:
 
 
 jobs:
@@ -31,12 +32,12 @@ jobs:
       run: |
         source .env/bin/activate
         pip install .[sklearn,tf,torch,testing]
+        pip uninstall -y tensorflow
 
     - 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:

diff --git a/README.md b/README.md
@@ -66,7 +66,7 @@ Choose the right framework for every part of a model's lifetime
 
 ## Installation
 
-This repo is tested on Python 3.5+, PyTorch 1.0.0+ and TensorFlow 2.0.0-rc1
+This repo is tested on Python 3.6+, PyTorch 1.0.0+ and TensorFlow 2.0.0-rc1
 
 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/).
 
@@ -163,8 +163,9 @@ At some point in the future, you'll be able to seamlessly move from pre-training
 13. **[XLM-RoBERTa](https://github.com/pytorch/fairseq/tree/master/examples/xlmr)** (from Facebook AI), released together with the paper [Unsupervised Cross-lingual Representation Learning at Scale](https://arxiv.org/abs/1911.02116) by Alexis Conneau*, Kartikay Khandelwal*, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov.
 14. **[MMBT](https://github.com/facebookresearch/mmbt/)** (from Facebook), released together with the paper a [Supervised Multimodal Bitransformers for Classifying Images and Text](https://arxiv.org/pdf/1909.02950.pdf) by Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Davide Testuggine.
 15. **[FlauBERT](https://github.com/getalp/Flaubert)** (from CNRS) released with the paper [FlauBERT: Unsupervised Language Model Pre-training for French](https://arxiv.org/abs/1912.05372) by Hang Le, Loïc Vial, Jibril Frej, Vincent Segonne, Maximin Coavoux, Benjamin Lecouteux, Alexandre Allauzen, Benoît Crabbé, Laurent Besacier, Didier Schwab.
-16. **[Other community models](https://huggingface.co/models)**, contributed by the [community](https://huggingface.co/users).
-17. Want to contribute a new model? We have added a **detailed guide and templates** to guide you in the process of adding a new model. You can find them in the [`templates`](./templates) folder of the repository. Be sure to check the [contributing guidelines](./CONTRIBUTING.md) and contact the maintainers or open an issue to collect feedbacks before starting your PR.
+16. **[BART](https://github.com/pytorch/fairseq/tree/master/examples/bart)** (from Facebook) released with the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/pdf/1910.13461.pdf) by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer.
+17. **[Other community models](https://huggingface.co/models)**, contributed by the [community](https://huggingface.co/users).
+18. Want to contribute a new model? We have added a **detailed guide and templates** to guide you in the process of adding a new model. You can find them in the [`templates`](./templates) folder of the repository. Be sure to check the [contributing guidelines](./CONTRIBUTING.md) and contact the maintainers or open an issue to collect feedbacks before starting your PR.
 
 These implementations have been tested on several datasets (see the example scripts) and should match the performances of the original implementations (e.g. ~93 F1 on SQuAD for BERT Whole-Word-Masking, ~88 F1 on RocStories for OpenAI GPT, ~18.3 perplexity on WikiText 103 for Transformer-XL, ~0.916 Peason R coefficient on STS-B for XLNet). You can find more details on the performances in the Examples section of the [documentation](https://huggingface.co/transformers/examples.html).
 
@@ -471,7 +472,7 @@ python ./examples/run_generation.py \
 
 Starting with `v2.2.2`, you can now upload and share your fine-tuned models with the community, using the <abbr title="Command-line interface">CLI</abbr> that's built-in to the library.
 
-**First, create an account on [https://huggingface.co/join](https://huggingface.co/join)**. Then:
+**First, create an account on [https://huggingface.co/join](https://huggingface.co/join)**. Optionally, join an existing organization or create a new one. Then:
 
 ```shell
 transformers-cli login
@@ -490,19 +491,26 @@ transformers-cli upload ./config.json [--filename folder/foobar.json]
 # (you can optionally override its filename, which can be nested inside a folder)
 ```
 
-Your model will then be accessible through its identifier, a concatenation of your username and the folder name above:
+If you want your model to be namespaced by your organization name rather than your username, add the following flag to any command:
+```shell
+--organization organization_name
+```
+
+Your model will then be accessible through its identifier, a concatenation of your username (or organization name) and the folder name above:
 ```python
 "username/pretrained_model"
+# or if an org:
+"organization_name/pretrained_model"
 ```
 
-**Please add a README.md model card** to the repo under `model_cards/` with: model description, training params (dataset, preprocessing, hyperparameters), evaluation results, intended uses & limitations, etc.
+**Please add a README.md model card** to the repo under `model_cards/` with: model description, training params (dataset, preprocessing, hardware used, hyperparameters), evaluation results, intended uses & limitations, etc.
 
 Your model now has a page on huggingface.co/models 🔥
 
 Anyone can load it from code:
 ```python
-tokenizer = AutoTokenizer.from_pretrained("username/pretrained_model")
-model = AutoModel.from_pretrained("username/pretrained_model")
+tokenizer = AutoTokenizer.from_pretrained("namespace/pretrained_model")
+model = AutoModel.from_pretrained("namespace/pretrained_model")
 ```
 
 List all your files on S3:

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -26,7 +26,7 @@
 # The short X.Y version
 version = u''
 # The full version, including alpha/beta/rc tags
-release = u'2.5.1'
+release = u'2.6.0'
 
 
 # -- General configuration ---------------------------------------------------

diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -103,3 +103,4 @@ The library currently contains PyTorch and Tensorflow implementations, pre-train
     model_doc/xlmroberta
     model_doc/flaubert
     model_doc/bart
+    model_doc/t5
diff --git a/docs/source/installation.md b/docs/source/installation.md
@@ -1,6 +1,6 @@
 # Installation
 
-Transformers is tested on Python 3.5+ and PyTorch 1.1.0
+Transformers is tested on Python 3.6+ and PyTorch 1.1.0
 
 ## With pip
 

diff --git a/docs/source/main_classes/pipelines.rst b/docs/source/main_classes/pipelines.rst
@@ -61,3 +61,8 @@ QuestionAnsweringPipeline
 
 .. autoclass:: transformers.QuestionAnsweringPipeline
 
+
+SummarizationPipeline
+==========================================
+
+.. autoclass:: transformers.SummarizationPipeline
diff --git a/docs/source/model_doc/t5.rst b/docs/source/model_doc/t5.rst
@@ -0,0 +1,69 @@
+T5
+----------------------------------------------------
+**DISCLAIMER:** This model is still a work in progress, if you see something strange,
+file a `Github Issue <https://github.com/huggingface/transformers/issues/new?assignees=&labels=&template=bug-report.md&title>`_
+
+Overview
+~~~~~
+The T5 model was presented in `Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer <https://arxiv.org/pdf/1910.10683.pdf>`_ by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu in 
+Here the abstract: 
+
+*Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. 
+In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. 
+Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. 
+By combining the insights from our exploration with scale and our new "Colossal Clean Crawled Corpus", we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. 
+To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.*
+
+The Authors' code can be found `here <https://github.com/google-research/text-to-text-transfer-transformer>`_ .
+
+Tips
+~~~~~~~~~~~~~~~~~~~~
+- T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised 
+  and supervised tasks and which each task is cast as a sequence to sequence task. 
+  Therefore T5 works well on a variety of tasks out-of-the-box by prepending a different prefix to the input corresponding to each task, e.g.: for translation: *translate English to German: ..., summarize: ...*.
+  For more information about the which prefix to use, it is easiest to look into Appendix D of the `paper <https://arxiv.org/pdf/1910.10683.pdf>`_ .
+- For sequence to sequence generation, it is recommended to use ``T5ForConditionalGeneration.generate()``. The method takes care of feeding the encoded input via cross-attention layers to the decoder and auto-regressively generating the decoder output.
+- T5 uses relative scalar embeddings. Encoder input padding can be done on the left and on the right.
+
+
+T5Config
+~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.T5Config
+    :members:
+
+
+T5Tokenizer
+~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.T5Tokenizer
+    :members: build_inputs_with_special_tokens, get_special_tokens_mask,
+        create_token_type_ids_from_sequences, save_vocabulary
+
+
+T5Model
+~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.T5Model
+    :members:
+
+
+T5ForConditionalGeneration
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.T5ForConditionalGeneration
+    :members:
+
+
+TFT5Model
+~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.TFT5Model
+    :members:
+
+
+TFT5ForConditionalGeneration
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. autoclass:: transformers.TFT5ForConditionalGeneration
+    :members:
diff --git a/docs/source/model_sharing.md b/docs/source/model_sharing.md
@@ -2,7 +2,7 @@
 
 Starting with `v2.2.2`, you can now upload and share your fine-tuned models with the community, using the <abbr title="Command-line interface">CLI</abbr> that's built-in to the library.
 
-**First, create an account on [https://huggingface.co/join](https://huggingface.co/join)**. Then:
+**First, create an account on [https://huggingface.co/join](https://huggingface.co/join)**. Optionally, join an existing organization or create a new one. Then:
 
 ```shell
 transformers-cli login
@@ -21,19 +21,26 @@ transformers-cli upload ./config.json [--filename folder/foobar.json]
 # (you can optionally override its filename, which can be nested inside a folder)
 ```
 
-Your model will then be accessible through its identifier, a concatenation of your username and the folder name above:
+If you want your model to be namespaced by your organization name rather than your username, add the following flag to any command:
+```shell
+--organization organization_name
+```
+
+Your model will then be accessible through its identifier, a concatenation of your username (or organization name) and the folder name above:
 ```python
 "username/pretrained_model"
+# or if an org:
+"organization_name/pretrained_model"
 ```
 
-**Please add a README.md model card** to the repo under `model_cards/` with: model description, training params (dataset, preprocessing, hyperparameters), evaluation results, intended uses & limitations, etc.
+**Please add a README.md model card** to the repo under `model_cards/` with: model description, training params (dataset, preprocessing, hardware used, hyperparameters), evaluation results, intended uses & limitations, etc.
 
 Your model now has a page on huggingface.co/models 🔥
 
 Anyone can load it from code:
 ```python
-tokenizer = AutoTokenizer.from_pretrained("username/pretrained_model")
-model = AutoModel.from_pretrained("username/pretrained_model")
+tokenizer = AutoTokenizer.from_pretrained("namespace/pretrained_model")
+model = AutoModel.from_pretrained("namespace/pretrained_model")
 ```
 
 List all your files on S3:
@@ -45,4 +52,4 @@ You can also delete unneeded files:
 
 ```shell
 transformers-cli s3 rm …
-```
+```
diff --git a/docs/source/pretrained_models.rst b/docs/source/pretrained_models.rst
@@ -275,7 +275,6 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
 |                   |                                                            | | FlauBERT large architecture                                                                                                         |
 |                   |                                                            | (see `details <https://github.com/getalp/Flaubert>`__)                                                                                |
 +-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
-+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
 | Bart              | ``bart-large``                                             | | 12-layer, 1024-hidden, 16-heads, 406M parameters                                                                                    |
 |                   |                                                            | (see `details <https://github.com/pytorch/fairseq/tree/master/examples/bart>`_)                                                       |
 |                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
@@ -285,6 +284,3 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
 |                   | ``bart-large-cnn``                                         | | 12-layer, 1024-hidden, 16-heads, 406M parameters       (same as base)                                                               |
 |                   |                                                            | | bart-large base architecture finetuned on cnn summarization task                                                                    |
 +-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
-
-
-.. <https://huggingface.co/transformers/examples.html>`__
diff --git a/examples/README.md b/examples/README.md
@@ -379,7 +379,7 @@ export SQUAD_DIR=/path/to/SQUAD
 
 python run_squad.py \
   --model_type bert \
-  --model_name_or_path bert-base-cased \
+  --model_name_or_path bert-base-uncased \
   --do_train \
   --do_eval \
   --do_lower_case \