Skip to content

Remove from_preset from fnet tokenizer #865

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 17, 2023
Merged

Remove from_preset from fnet tokenizer #865

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 0 additions & 53 deletions keras_nlp/models/f_net/f_net_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,15 +15,11 @@
"""FNet tokenizer."""

import copy
import os

from tensorflow import keras

from keras_nlp.api_export import keras_nlp_export
from keras_nlp.models.f_net.f_net_presets import backbone_presets
from keras_nlp.tokenizers.sentence_piece_tokenizer import SentencePieceTokenizer
from keras_nlp.utils.python_utils import classproperty
from keras_nlp.utils.python_utils import format_docstring


@keras_nlp_export("keras_nlp.models.FNetTokenizer")
Expand Down Expand Up @@ -92,52 +88,3 @@ def __init__(self, proto, **kwargs):
@classproperty
def presets(cls):
return copy.deepcopy(backbone_presets)

@classmethod
@format_docstring(names=", ".join(backbone_presets))
def from_preset(
cls,
preset,
**kwargs,
):
"""Instantiate an FNet tokenizer from preset vocabulary.

Args:
preset: string. Must be one of {{names}}.

Examples:
```python
# Load a preset tokenizer.
tokenizer = keras_nlp.models.FNetTokenizer.from_preset(
"f_net_base_en",
)

# Tokenize some input.
tokenizer("The quick brown fox tripped.")

# Detokenize some input.
tokenizer.detokenize([5, 6, 7, 8, 9])
```
"""
if preset not in cls.presets:
raise ValueError(
"`preset` must be one of "
f"""{", ".join(cls.presets)}. Received: {preset}."""
)
metadata = cls.presets[preset]

spm_proto = keras.utils.get_file(
"vocab.spm",
metadata["spm_proto_url"],
cache_subdir=os.path.join("models", preset),
file_hash=metadata["spm_proto_hash"],
)

config = metadata["preprocessor_config"]
config.update(
{
"proto": spm_proto,
},
)

return cls.from_config({**config, **kwargs})