chi2liu

mamba-gpt-3b

It is almost the best 3B model in the current open source industry, surpassing Dolly v2-3b, open lama-3b, and even outperforming the EleutherAI/pythia-12b model in terms of performance. Can refer to open_llm_leaderboard

Backpropagation

chi2liu.github.io

Personal's Pages

advisor

Open-source implementation of Google Vizier for hyper parameters tuning

conda

OS-agnostic, system-level binary package manager and ecosystem

datatable

data.table for Python

dbscanpp

koalas

Koalas: pandas API on Apache Spark

LLaMA-Efficient-Tuning

Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan)

mars

Mars is a tensor-based unified framework for large-scale data computation which scales Numpy, pandas, Scikit-learn and Python functions.

Paddle

PArallel Distributed Deep LEarning （『飞桨』核心框架，高性能单机、分布式训练和跨平台部署）

seldon-core

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

word2vec_cbow

this is a high performance cuda porting of cbow model of word2vec