From 6758eee17163efc742fba991809aa379e965c5f5 Mon Sep 17 00:00:00 2001 From: Stas Bekman Date: Mon, 4 Jan 2021 20:37:52 -0800 Subject: [PATCH] add experimental warning --- src/transformers/models/gpt2/modeling_gpt2.py | 2 ++ src/transformers/models/t5/modeling_t5.py | 2 ++ 2 files changed, 4 insertions(+) diff --git a/src/transformers/models/gpt2/modeling_gpt2.py b/src/transformers/models/gpt2/modeling_gpt2.py index bb8046c0e2f0..609ed77409a8 100644 --- a/src/transformers/models/gpt2/modeling_gpt2.py +++ b/src/transformers/models/gpt2/modeling_gpt2.py @@ -479,6 +479,8 @@ class GPT2DoubleHeadsModelOutput(ModelOutput): Whether or not to return a :class:`~transformers.file_utils.ModelOutput` instead of a plain tuple. """ PARALLELIZE_DOCSTRING = r""" + This is an experimental feature and is a subject to change at a moment's notice. + Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices. diff --git a/src/transformers/models/t5/modeling_t5.py b/src/transformers/models/t5/modeling_t5.py index 0ce2be3c62ac..c2424f9b467f 100644 --- a/src/transformers/models/t5/modeling_t5.py +++ b/src/transformers/models/t5/modeling_t5.py @@ -179,6 +179,8 @@ def load_tf_weights_in_t5(model, config, tf_checkpoint_path): # - PreTrainedModel for the models (it-self a sub-class of torch.nn.Module) #################################################### PARALLELIZE_DOCSTRING = r""" + This is an experimental feature and is a subject to change at a moment's notice. + Uses a device map to distribute attention modules of the model across several devices. If no device map is given, it will evenly distribute blocks across all devices.