920232796/bert_seq2seq
A lightweight PyTorch framework for seq2seq tasks using BERT-style models with UniLM, supporting summarization, classification, NER, and text generation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of BERT-based seq2seq using the UniLM approach. It supports multiple pretrained models including BERT, RoBERTa, GPT2, and T5, and enables tasks such as automatic summarization, text classification, sentiment analysis, named entity recognition, and relation extraction. Users configure model type via model_name and task type via model_class, with example scripts provided for each task. A distributed training version supporting multi-GPU training is also available.
Frequently asked
- What is 920232796/bert_seq2seq?
- A lightweight PyTorch framework for seq2seq tasks using BERT-style models with UniLM, supporting summarization, classification, NER, and text generation.
- Is bert_seq2seq open source?
- Yes — 920232796/bert_seq2seq is open source, released under the Apache-2.0 license.
- What language is bert_seq2seq written in?
- 920232796/bert_seq2seq is primarily written in Python.
- How popular is bert_seq2seq?
- 920232796/bert_seq2seq has 1.3k stars on GitHub.
- Where can I find bert_seq2seq?
- 920232796/bert_seq2seq is on GitHub at https://github.com/920232796/bert_seq2seq.