practicingman/bert_serving
export bert model for serving
This project helps machine learning engineers efficiently deploy trained BERT models for live predictions. It takes a pre-trained or fine-tuned BERT model and exports it into a 'SavedModel' format, optimized for quick serving. This is useful for developers who need to integrate BERT's natural language understanding capabilities into applications with low latency requirements.
141 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer looking to deploy a BERT model for real-time inference in a production environment.
Not ideal if you are looking for a high-level API or a pre-built serving solution that doesn't require direct manipulation of TensorFlow's export functions.
Stars
141
Forks
36
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 12, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/practicingman/bert_serving"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
JayYip/m3tl
BERT for Multitask Learning
920232796/bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
sileod/tasknet
Easy modernBERT fine-tuning and multi-task learning
graykode/toeicbert
TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.