利用HuggingFace的官方下载工具从镜像网站进行高速下载。

leaked prompts of GPTs

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

A high-throughput and memory-efficient inference and serving engine for LLMs

terashuf shuffles multi-terabyte text files using limited memory

企业微信的python封装接口，简易上手，开箱即用，一行代码实现消息推送。A more convenient python wrapper interface of corpwechat(wework, wecom) official API, use only one line of code to send your messages to your corpwechat(wework,…

Wechat Chat History Exporter 微信聊天记录导出备份程序

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

MARISA: Matching Algorithm with Recursively Implemented StorAge

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

Oscar and VinVL

Python library and shell utilities to monitor filesystem events.

🕷️ The pipeline for the OSCAR corpus

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Tools to download and cleanup Common Crawl data

Chinese version of GPT2 training code, using BERT tokenizer.

probability distribution checker for poem

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

中文公开聊天语料库

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

A paper list of automatic poetry generation, analysis, translation, etc.

Code for the paper "Language Models are Unsupervised Multitask Learners"

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。

maps between 1-D space filling hilbert curve and N-D coordinates

GPT-3: Language Models are Few-Shot Learners

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"