include the output layer in the model using the pretrained weights #18
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for that. I've ended up taking a more modular approach in the first pip release of the library. |
Closed
stevezheng23
added a commit
to stevezheng23/transformers
that referenced
this pull request
Mar 24, 2020
fix at issues in roberta/berta modeling (cont.)
2 tasks
wamartin-aml
pushed a commit
to wamartin-aml/transformers
that referenced
this pull request
Nov 1, 2021
…ortmodule Permit DDP wrapping for ORTModule
rraminen
pushed a commit
to rraminen/transformers
that referenced
this pull request
Oct 27, 2022
…t_HF Enable ORT for HuggingFace workloads
jlamypoirier
added a commit
to jlamypoirier/transformers
that referenced
this pull request
Apr 4, 2023
jameshennessytempus
pushed a commit
to jameshennessytempus/transformers
that referenced
this pull request
Jun 1, 2023
1 task
jonb377
pushed a commit
to jonb377/hf-transformers
that referenced
this pull request
Nov 3, 2023
Summary: This pull requests fix a bug in pytorch-tpu#17 where it forgot to guard 2D sharding for activations and inputs. Test Plan: N/A.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is to be able to load the final output layer (bert.output_layer) from the TensorFlow pre-trained model.
In particular, it is a fully connected layer that is used to map the final hidden layer to the vocabulary size, to then apply the softmax, as follows:
logits = bert.output_layer(sequence_output)
log_softmax = nn.LogSoftmax(dim=-1)
log_probs = log_softmax(logits)