SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Clarified PreTrainedModel.from_pretrained warning messages in documentation.

Browse Source
This commit is contained in:
LysandreJik
2019-08-08 19:04:34 -04:00
parent f2b300df6b
commit 3566d27919
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
pytorch_transformers/modeling_utils.py
View File

@@ -365,6 +365,11 @@ class PreTrainedModel(nn.Module):
The model is set in evaluation mode by default using ``model.eval()`` (Dropout modules are deactivated) The model is set in evaluation mode by default using ``model.eval()`` (Dropout modules are deactivated)
To train the model, you should first set it back in training mode with ``model.train()`` To train the model, you should first set it back in training mode with ``model.train()``
The warning ``Weights from XXX not initialized from pretrained model`` means that the weights of XXX do not come pre-trained with the rest of the model.
It is up to you to train those weights with a downstream fine-tuning task.
The warning ``Weights from XXX not used in YYY`` means that the layer XXX is not used by YYY, therefore those weights are discarded.
Parameters: Parameters:
pretrained_model_name_or_path: either: pretrained_model_name_or_path: either: