Release: v4.0.1

* conda

* Guide

* correct tag

* Update README.md

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update docs/source/installation.md

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Sylvain's comments

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

.circleci/deploy.sh

@@ -53,4 +53,4 @@ deploy_doc "3ebb1b3" v3.2.0
 deploy_doc "0613f05" v3.3.1
 deploy_doc "eb0e0ce" v3.4.0
 deploy_doc "818878d" v3.5.1
-deploy_doc "c781171" # v4.0.0 Latest stable release
+deploy_doc "28d3ccd" # v4.0.1 Latest stable release

.github/workflows/release-conda.yml

@@ -4,9 +4,6 @@ on:
   push:
     tags:
       - v*
-    branches:
-      - v4.0.0-release
-
 
 env:
   ANACONDA_API_TOKEN: ${{ secrets.ANACONDA_API_TOKEN }}

docs/source/_static/js/custom.js

@@ -1,10 +1,10 @@
 // These two things need to be updated at each release for the version selector.
 // Last stable version
-const stableVersion = "v4.0.0"
+const stableVersion = "v4.0.1"
 // Dictionary doc folder to label
 const versionMapping = {
     "master": "master",
-    "v4.0.0": "v4.0.0",
+    "": "v4.0.0/v4.0.1",
     "v3.5.1": "v3.5.0/v3.5.1",
     "v3.4.0": "v3.4.0",
     "v3.3.1": "v3.3.0/v3.3.1",

docs/source/conf.py

@@ -26,7 +26,7 @@ author = u'huggingface'
 # The short X.Y version
 version = u''
 # The full version, including alpha/beta/rc tags
-release = u'4.0.0'
+release = u'4.0.1'
 
 
 # -- General configuration ---------------------------------------------------

setup.py

@@ -119,7 +119,7 @@ extras["dev"] = extras["all"] + extras["testing"] + extras["quality"] + extras["
 
 setup(
     name="transformers",
-    version="4.0.0",
+    version="4.0.1",
     author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Sam Shleifer, Patrick von Platen, Sylvain Gugger, Google AI Language Team Authors, Open AI team Authors, Facebook AI Authors, Carnegie Mellon University Authors",
     author_email="thomas@huggingface.co",
     description="State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch",

src/transformers/__init__.py

@@ -2,7 +2,7 @@
 # There's no way to ignore "F401 '...' imported but unused" warnings in this
 # module, but to preserve other warnings. So, don't check this module at all.
 
-__version__ = "4.0.0"
+__version__ = "4.0.1"
 
 # Work around to update TensorFlow's absl.logging threshold which alters the
 # default Python logging output behavior when present.

src/transformers/models/auto/tokenization_auto.py

@@ -342,7 +342,13 @@ class AutoTokenizer:
             if tokenizer_class_fast and (use_fast or tokenizer_class_py is None):
                 return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
             else:
-                return tokenizer_class_py.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
+                if tokenizer_class_py is not None:
+                    return tokenizer_class_py.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
+                else:
+                    raise ValueError(
+                        "This tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed "
+                        "in order to use this tokenizer."
+                    )
 
         raise ValueError(
             "Unrecognized configuration class {} to build an AutoTokenizer.\n"

src/transformers/trainer.py

@@ -538,7 +538,7 @@ class Trainer:
             self.args.output_dir = checkpoint_dir
             output_dir = os.path.join(self.args.output_dir, f"{PREFIX_CHECKPOINT_DIR}-{self.state.global_step}")
             self.save_model(output_dir)
-            if self.is_world_master():
+            if self.is_world_process_zero():
                 self.state.save_to_json(os.path.join(output_dir, "trainer_state.json"))
                 torch.save(self.optimizer.state_dict(), os.path.join(output_dir, "optimizer.pt"))
                 torch.save(self.lr_scheduler.state_dict(), os.path.join(output_dir, "scheduler.pt"))