maximal update parametrization (µP)

Ongoing research training transformer models at scale

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

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

爬取关注列表中微博账号的微博

Rasa-Doctor-Friende.A chinese medical chatbot based on Neo4j knowledge graph and Rasa.

A platform for building proxies to bypass network restrictions.

常用中国网站白名单，纯列表，用于 SwitchyOmega，控制不走代理的网站。

自己使用的白名单pac文件，不定时更新常见域名

gfw_whitelist

Chinese, English NER, English-Chinese machine translation dataset. 中英文实体识别数据集，中英文机器翻译数据集, 中文分词数据集

Collections of Chinese NLP corpus

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation

A complete computer science study plan to become a software engineer.

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.

Multi-turn dialogue baselines written in PyTorch

我的 OI 课件

HRED VHRED VHCR for Multi-Turn Dialogue Systems

Google Research

Reformer, the efficient Transformer, in Pytorch

BERT score for text generation

Embedding-based evaluation metrics for dialogue generation.

PyTorch Implementation of "A Hierarchical Latent Structure for Variational Conversation Modeling" (NAACL 2018 Oral)

A dataset containing human-human knowledge-grounded open-domain conversations.

OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.