BertMaskedLM Task Model and Preprocessor #774
Merged
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
|
@mattdangerw This PR is ready for review. |
Cyber-Machine
changed the title
|
@Cyber-Machine use |
shivance
suggested changes
Feb 25, 2023
…nto BertMaskedLM
|
@mattdangerw @abheesht17 This PR is ready for review. |
… into BertMaskedLM
mattdangerw
approved these changes
Mar 3, 2023
| @keras.utils.register_keras_serializable(package="keras_nlp") | ||
| class BertMaskedLMPreprocessor(BertPreprocessor): | ||
| """BERT preprocessing for the masked language modeling task. | ||
| This preprocessing layer will prepare inputs for a masked language modeling |
There was a problem hiding this comment.
Looks like the empty newlines from the version you copied from got removed. (github does this for some reason)
Can you add them back in throughout this docstring?
| self.assertAllEqual( | ||
| x["padding_mask"], | ||
| [ | ||
| True, |
There was a problem hiding this comment.
If possible, shorted these examples so we don't take up so much vertical space here.
You should be able to pass 0s and 1s here which should help, we do that for other tests.
abheesht17
reviewed
Mar 3, 2023
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| # See the License for the specific language governing permissions and | ||
| # limitations under the License. | ||
| """BERT masked lm model.""" |
| intermediate_dim=3072, | ||
| max_sequence_length=12 | ||
| ) | ||
| # Create a BERT masked_lm and fit the data. |
There was a problem hiding this comment.
"Crete a BERT masked LM model and fit the data."
|
Thank you! This is great! |
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Outdated suggestions cannot be applied.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.
Fixes #719
I have made the following changes, but I am still, working on the process:
BertTokenizerto expect a mask token.BertMaskedLMPreprocessorpreprocessor layer and tests.BertMaskedLMtask model and tests.keras_nlp/models/__init__.pyto exportBertMaskedLMandBertMaskedLMPreprocessor.