textbox

We have hosted the application textbox in order to run this application in our online workstations with Wine or directly.

Quick description about textbox:

TextBox 2.0 is an up-to-date text generation library based on Python and PyTorch focusing on building a unified and standardized pipeline for applying pre-trained language models to text generation. From a task perspective, we consider 13 common text generation tasks such as translation, story generation, and style transfer, and their corresponding 83 widely-used datasets. From a model perspective, we incorporate 47 pre-trained language models/modules covering the categories of general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight models (modules). From a training perspective, we support 4 pre-training objectives and 4 efficient and robust training strategies, such as distributed data parallel and efficient generation. Compared with the previous version of TextBox, this extension mainly focuses on building a unified, flexible, and standardized framework for better supporting PLM-based text generation models.

Features:

• It is a significant innovation focusing on comprehensive tasks and PLMs
• It is designed to be unified in implementation and interface
• It can faithfully reproduce the results reported in existing work
• TextBox 2.0 provides four pre-training objectives to help users pre-train a model from scratch
• Four useful training methods are provided for improving the optimization of PLMs
• To support the rapid progress of PLMs on text generation, TextBox 2.0 incorporates 47 models/modules

Programming Language: Python.
Categories: