SuperXiang

AttnPacker

Code and Pre-Trained Models for "AttnPacker: An end-to-end deep learning method for protein side-chain packing"

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

codealpaca

ContinualLM

An Extensible Continual Learning Framework Focused on Language Models (LMs)

DIFFormer

The official implementation for ICLR23 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"

dl_binder_design

efficient-evolution

Efficient evolution from protein language models

Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

GeoStab

GPT-NER

how-to-train-tokenizer

怎么训练一个LLM分词器

long_llama

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

mdtraj

An open library for the analysis of molecular dynamics trajectories

mixture-of-experts

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

mlmc

Code for fine-tuning transformers (XLNet, Bert and GPT-2) on binary, multi-class and multi-label sequence classification tasks.

MULTICOM3

The software system of predicting protein tertiary and quaternary structures. It is prepared for CASP15 by BMLab.

multipack_sampler

Multipack distributed sampler for fast padding-free training of LLMs

PaddleFleetX

Paddle Distributed Training Examples. 飞桨分布式训练示例 Resnet Bert GPT MOE DataParallel ModelParallel PipelineParallel HybridParallel AutoParallel Zero Sharding Recompute GradientMerge Offload AMP DGC LocalSGD Wide&Deep

RFdiffusion

Code for running RFdiffusion

RoseTTAFold2

SecBERT

pretrained BERT model for cyber security text, learned CyberSecurity Knowledge

sentencepiece_chinese_bpe

使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。

sk-iterative-planner

Iterative Planner for Semantic Kernel

SpeedPPI

Rapid protein-protein interaction network creation from multiple sequence alignments with Deep Learning

Stable-Alignment

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

VardaGPT

Associative memory-enhanced GPT-2 model

mesh

Mesh TensorFlow: Model Parallelism Made Easier

MT-LLaMA

Multi-Task instruction-tuned LLaMA

PdfGptIndexer

An efficient tool for indexing and searching PDF text data using OpenAI API and FAISS (Facebook AI Similarity Search) index, designed for rapid information retrieval and superior search accuracy.

PLSC

Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.