BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

GPT2 for Chinese chitchat/GPT2 model for Chinese chitchat (implements DialoGPT's MMI idea)

Chinese nlp solution (large model, data, model, training, reasoning)

RoBERTA Chinese pre training model: RoBERTA for Chinese

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Pytorch implements Bert to do the seq2seq task. Using the unilm scheme, it can now also do tasks such as automatic summarization, text classification, sentiment analysis, NER, part of speech tagging, etc. It supports the t5 model and GPT2 to continue writing articles.

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

Chinese NewsTitle Generation Project by GPT2.

Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation

TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on.

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

Pre-trained Transformers for Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic ELECTRA)

Code for producing Japanese pretrained models provided by rinna Co., Ltd.

A PyTorch implementation of "Graph Wavelet Neural Network" (ICLR 2019)

Easy to use CPM for Chinese text generation

Implementation of common tasks in NLP field, including new word discovery, word vector based on pythoch, Chinese text classification, entity recognition, abstract text generation, sentence similarity judgment, triplet extraction, pre training model, etc.

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

MindSpore online courses: Step into LLM

1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.

텐서플로2와 머신러닝으로 시작하는 자연어처리 (로지스틱회귀부터 BERT와 GPT3까지) 실습자료