Chinese version of GPT2 training code, using BERT tokenizer.
-
Updated
Feb 27, 2023 - Python
Chinese version of GPT2 training code, using BERT tokenizer.
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/
Large-scale pretraining for dialogue
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
DELTA is a deep learning based natural language and speech processing platform.
A modular RL library to fine-tune language models to human preferences
TextBox 2.0 is a text generation library with pre-trained language models
Summarization Papers
Code for Defending Against Neural Fake News, https://rowanzellers.com/grover/
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
Accelerated Text is a no-code natural language generation platform. It will help you construct document plans which define how your data is converted to textual descriptions varying in wording and structure.
The codes of paper "Long Text Generation via Adversarial Training with Leaked Information" on AAAI 2018. Text generation using GAN and Hierarchical Reinforcement Learning.
Author: Wenhao Yu (wyu1@nd.edu). ACM Computing Survey'22. Reading list for knowledge-enhanced text generation, with a survey.
Add a description, image, and links to the text-generation topic page so that developers can more easily learn about it.
To associate your repository with the text-generation topic, visit your repo's landing page and select "manage topics."