Xu Song

bert-as-language-model. BERT as language model, fork from https://github.com/google-research/bert

hexo-auto-category. Generate categories automatically for each post in Hexo

k-plug. K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce (Findings of EMNLP 2021)

attention-pytorch. unfinished ...

PrettyPrint. Chrome Extension for web page print

prince. Python

movielens. movielens data analysis

gpt-neox. An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

tensorflow-multi-gpu. Python

tensor2tensor-eager. Python

tokenizer-arena.

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

DiffCSE. Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"

hred-tf. Hierarchical Recurrent Encoder-Decoder in TensorFlow

traceid. https://pypi.org/project/traceid/

chat.petals.ml. Chatbot web app + HTTP and Websocket endpoints for BLOOM-176B inference with the Petals client

petals. 🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

SparrowRecSys. A Deep Learning Recommender System

hexo. A fast, simple & powerful blog framework, powered by Node.js.

tensorflow_multi_language. tensorflow in python, C++, js, Java

xu-song.

gitignore. A collection of useful .gitignore templates

pycorrector. pycorrector is a toolkit for text error correction. 文本纠错，Kenlm，ConvSeq2Seq，BERT，MacBERT，ELECTRA，ERNIE，Transformer，T5等模型实现，开箱即用。

tensor2tensor. Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

SMSBoom. 短信轰炸/短信测压/ | 一个健壮免费的python短信轰炸程序，专门炸坏蛋蛋，百万接口，多线程全自动添加有效接口，支持异步协程百万并发，全免费的短信轰炸工具！！hongkonger开发全网首发！！

rasa. 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

machine-learning. Jupyter Notebook

Awesome-Text-to-Image. A Survey on Text-to-Image Generation/Synthesis.

xu-song.github.io. A multipurpose one page Bootstrap theme created by Start Bootstrap

transformers. 🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

CrossWOZ. A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

python-Levenshtein. The Levenshtein Python C extension module contains functions for fast computation of Levenshtein distance and string similarity

pyreadline. pyreadline repository

bitarray. efficient arrays of booleans for Python

recommenders. Best Practices on Recommendation Systems

jieba. 结巴中文分词