QizhiPei

LLM101n

LLM101n: Let's build a Storyteller

llama3

The official Meta Llama 3 GitHub site

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

LogicStack-LeetCode

公众号「宫水三叶的刷题日记」刷穿 LeetCode 系列文章源码

DeepSpeedExamples

Example models using DeepSpeed

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

summarize-from-feedback

Code for "Learning to summarize from human feedback"

PaddleHelix

Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

MergeLM

Codebase for Merging Language Models (ICML 2024)

AlphaFold3

Implementation of Alpha Fold 3 from the paper: "Accurate structure prediction of biomolecular interactions with AlphaFold3" in PyTorch

ChatGPT-Academic-Prompt

Use ChatGPT for academic writing

SimCTG

[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation

CharacterEval

InstructPLM

The first large protein language model trained follows structure instructions.

tfold

open source code for Tencent tFold

Clipboard-to-SMILES-Converter

Converts clipboard content to smiles and much more

PoseBench

Comprehensive benchmarking of protein-ligand structure generation methods (ICML 2024 AI4Science)

ProtT3

Source code for ACL 2024 paper: "ProtT3: Protein-to-Text Generation for Text-based Protein Understanding"

ProteinDT

DeProt

Code for DeProt. A protein language model with quantizied structure and disentangled attention

ProTrek

ProTrek: Navigating the Protein Universe through Tri-Modal Contrastive Learning

Prompt-DDG

Code for ICML 2024 paper "Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning"

proteinclip

Contrastive learning harmonizing protein language models and natural language models

Panacea

SLM4CRP

A Self-feedback Knowledge Elicitation Approach for Chemical Reaction Predictions

DiffIUPAC

Diffusion-based generative drug-like molecular editing with chemical natural language

CycleAlign

Repository for our ACL submission "CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment"

KyGao.github.io

AcadHomepage: A Modern and Responsive Academic Personal Homepage

KyGao