Hugging-Face-Supporter/tftokenizers
Use Huggingface Transformer and Tokenizers as Tensorflow Reusable SavedModels
This tool helps machine learning engineers package Hugging Face tokenizers with TensorFlow models into a single, portable SavedModel. You input a Hugging Face model and tokenizer, and it outputs a self-contained TensorFlow SavedModel. This is used by developers deploying natural language processing models into production TensorFlow environments.
No commits in the last 6 months. Available on PyPI.
Use this if you need to deploy Hugging Face Transformer models with their tokenizers as a single TensorFlow Reusable SavedModel.
Not ideal if you are working with non-BERT Hugging Face models, as only BERT-based tokenizers are currently supported.
Stars
10
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 29, 2022
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Hugging-Face-Supporter/tftokenizers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
huggingface/tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
megagonlabs/ginza-transformers
Use custom tokenizers in spacy-transformers
Kaleidophon/token2index
A lightweight but powerful library to build token indices for NLP tasks, compatible with major...
NVIDIA/Cosmos-Tokenizer
A suite of image and video neural tokenizers
wangcongcong123/ttt
A package for fine-tuning Transformers with TPUs, written in Tensorflow2.0+