Name: Yusheng (Ethan) Su
Type: User
Company: Tsinghua University (Graduated)
Bio: #ML #NLP #LLM(er).
Goal: Building a model toward AGI.
Twitter: thu_yushengsu
Location: California, USA
Blog: https://yushengsu-thu.github.io/
Yusheng (Ethan) Su's Projects
Efficient Training (including pre-training and fine-tuning) for Big Models
Predict (User pattern): Predict every user's Commercial Click-through-rate with random forest model and kdd-naggle cvs data
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
for Data Science class on Coursera
Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
This is a curated list of "Embodied Agents" research. Read this repository for the latest updates. Feel free to raise pull requests and launch the disscussion!
LLM Reasoning
Add AgentVerse paper link
LLM training in simple, raw C/CUDA
An IDE layer for Neovim with sane defaults. Completely free and community driven.
distributed trainer for LLMs
Efficient, Low-Resource, Distributed transformer implementation based on BMTrain
Explore the µP
105學年度 國立政治大學 資訊科學系 軟體工程 DApp 範例
A well configured and structured Neovim.
RPG_Game
Exploring the Impact of Model Scaling on Parameter-efficient Tuning Methods
pre-training_cook
Must-read papers on prompt-based tuning for pre-trained language models.
Science driven scaling: to pursue scientific principles bebind scaling and use them to guide next-generation model development, where the subareas include data engineering, long context, efficiency, and science of language models
my vim configure
All Tuning works in SuperAlignment
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
An Open-Ended Embodied Agent with Large Language Models
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes