An open-source tool-augmented conversational language model from Fudan University

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

中文nlp解决方案(大模型、数据、模型、训练、推理)

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

A modular RL library to fine-tune language models to human preferences

DELTA is a deep learning based natural language and speech processing platform.

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

TextBox 2.0 is a text generation library with pre-trained language models

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。

Summarization Papers

Code for Defending Against Neural Fake News, https://rowanzellers.com/grover/

TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.

📖 Paper reading list in dialogue systems and natural language generation (constantly updating 🤗).