Change default cache path (#8734)

* Change default cache path

* Document changes

* Apply suggestions from code review
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

docs/source/installation.md

@@ -70,15 +70,15 @@ to check 🤗 Transformers is properly installed.
 
 This library provides pretrained models that will be downloaded and cached locally. Unless you specify a location with
 `cache_dir=...` when you use methods like `from_pretrained`, these models will automatically be downloaded in the
-folder given by the shell environment variable ``TRANSFORMERS_CACHE``. The default value for it will be the PyTorch
-cache home followed by ``/transformers/`` (even if you don't have PyTorch installed). This is (by order of priority):
+folder given by the shell environment variable ``TRANSFORMERS_CACHE``. The default value for it will be the Hugging
+Face cache home followed by ``/transformers/``. This is (by order of priority):
 
-  * shell environment variable ``TORCH_HOME``
-  * shell environment variable ``XDG_CACHE_HOME`` + ``/torch/``
-  * default: ``~/.cache/torch/``
+  * shell environment variable ``HF_HOME`` 
+  * shell environment variable ``XDG_CACHE_HOME`` + ``/huggingface/``
+  * default: ``~/.cache/huggingface/``
 
 So if you don't have any specific environment variable set, the cache directory will be at
-``~/.cache/torch/transformers/``.
+``~/.cache/huggingface/transformers/``.
 
 **Note:** If you have set a shell environment variable for one of the predecessors of this library
 (``PYTORCH_TRANSFORMERS_CACHE`` or ``PYTORCH_PRETRAINED_BERT_CACHE``), those will be used if there is no shell

src/transformers/file_utils.py

@@ -203,8 +203,28 @@ except ImportError:
     _tokenizers_available = False
 
 
-default_cache_path = os.path.join(torch_cache_home, "transformers")
-
+old_default_cache_path = os.path.join(torch_cache_home, "transformers")
+# New default cache, shared with the Datasets library
+hf_cache_home = os.path.expanduser(
+    os.getenv("HF_HOME", os.path.join(os.getenv("XDG_CACHE_HOME", "~/.cache"), "huggingface"))
+)
+default_cache_path = os.path.join(hf_cache_home, "transformers")
+
+# Onetime move from the old location to the new one if no ENV variable has been set.
+if (
+    os.path.isdir(old_default_cache_path)
+    and "PYTORCH_PRETRAINED_BERT_CACHE" not in os.environ
+    and "PYTORCH_TRANSFORMERS_CACHE" not in os.environ
+    and "TRANSFORMERS_CACHE" not in os.environ
+):
+    logger.warn(
+        "In Transformers v4.0.0, the default path to cache downloaded models changed from "
+        "'~/.cache/torch/transformers' to '~/.cache/huggingface/transformers'. Since you don't seem to have overridden "
+        "and '~/.cache/torch/transformers' is a directory that exists, we're moving it to "
+        "'~/.cache/huggingface/transformers' to avoid redownloading models you have already in the cache. You should "
+        "only see this message once."
+    )
+    shutil.move(old_default_cache_path, default_cache_path)
 
 PYTORCH_PRETRAINED_BERT_CACHE = os.getenv("PYTORCH_PRETRAINED_BERT_CACHE", default_cache_path)
 PYTORCH_TRANSFORMERS_CACHE = os.getenv("PYTORCH_TRANSFORMERS_CACHE", PYTORCH_PRETRAINED_BERT_CACHE)