Traditional Mandarin LLMs for Taiwan

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Finetune LLaMA-7B with Chinese instruction datasets

Public facing notes page

A Traditional-Chinese instruction-following model with datasets based on Alpaca.

LLM inference in C/C++

Physical Symbolic Optimization

Open source code for AlphaFold 2.

VAE in feature extraction help predicting stock

Python 網頁爬蟲入門實戰

Python wrapper for TA-Lib (http://ta-lib.org/).

SFI_2020JulyCourse

Reptile on supervised meta-learning datasets