tftokenizers 0.1.0

tftokenizers Use Huggingface Transformer and Tokenizers as Tensorflow Reusable SavedModels.

TFtftransformers

Converting Hugginface tokenizers to Tensorflow tokenizers. The main reason is to be able to bundle the tokenizer and model into one Reusable SavedModel.

---

Source Code: https://github.com/Hugging-Face-Supporter/tftransformers

---

Example

This is an example of how one can use Huggingface model and tokenizers bundled together as a Reusable SavedModel and yields the same result as using the model and tokenizer from Huggingface 🤗

import tensorflow as tf
from tftransformers.model import TFModel
from tftransformers.tokenizer import TFAutoTokenizer
from transformers import TFAutoModel

# Load base models from Huggingface
model_name = "bert-base-cased"
model = TFAutoModel.from_pretrained(model_name)

# Load converted TF tokenizer
tokenizer = TFAutoTokenizer(model_name)

# Create a TF Reusable SavedModel
custom_model = TFModel(model=model, tokenizer=tokenizer)

# Tokenizer and model can handle `tf.Tensors` or regular strings
tf_string = tf.constant(["Hello from Tensorflow"])
s1 = "SponGE bob SQuarePants is an avenger"
s2 = "Huggingface to Tensorflow tokenizers"
s3 = "Hello, world!"

output = custom_model(tf_string)
output = custom_model([s1, s2, s3])

# You can also pass arguments, similar to Huggingface tokenizers
output = custom_model(
    [s1, s2, s3],
    max_length=512,
    padding="max_length",
)
print(output)

# Save tokenizer
saved_name = "reusable_bert_tf"
tf.saved_model.save(custom_model, saved_name)

# # Load tokenizer
reloaded_model = tf.saved_model.load(saved_name)
output = reloaded_model([s1, s2, s3])
print(output)

Setup

git clone https://github.com/Hugging-Face-Supporter/tftransformers.git
cd tf_transformers
poetry install
poetry shell

Run

To convert a Huggingface tokenizer to Tensorflow, first choose one from the models or tokenizers from the Huggingface hub to download.

NOTE

Currently only BERT models work with the converter.

Download

First download tokenizers from the hub by name. Either run the bash script do download multiple tokenizers or download a single tokenizer with the python script.

The idea is to eventually only to automatically download and convert

python tf_transformers/download.py -n bert-base-uncased
bash scripts/download_tokenizers.sh

Convert

Convert downloaded tokenizer from Huggingface format to Tensorflow

python tf_transformers/convert.py

Before Commit

make build

WIP

• Convert a BERT tokenizer from Huggingface to Tensorflow
• Make a TF Reusabel SavedModel with Tokenizer and Model in the same class. Emulate how the TF Hub example for BERT works.
• Find methods for identifying the base tokenizer model and map those settings and special tokens to new tokenizers
• Extend the tokenizers to more tokenizer types and identify them from a huggingface model name
• Document how others can use the library and document the different stages in the process
• Convert other tokenizers. Identify limitations
• Improve the conversion pipeline (s.a. Download and export files if not passed in or available locally)
• Support encoding of two sentences at a time Ref
• Allow the tokenizers to be used for Masking (MLM) Ref