aimetrics

PERSIA

High performance distributed framework for training deep learning recommendation models based on PyTorch.

transformer_user_action

Transformer-based Realtime User Action Model for Recommendation at Pinterest

alpaca-lora

Instruct-tune LLaMA on consumer hardware

awesome-chatgpt-prompts-zh

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

annotated-transformer

An annotated implementation of the Transformer paper.

bigscience

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

Chinese-BERT-wwm

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

clip-retrieval

Easily compute clip embeddings and build a clip retrieval system with them

Curvature-Learning-Framework

Curvlearn, a Tensorflow based non-Euclidean deep learning framework.

dalle-mini

DALL·E Mini - Generate images from a text prompt

defer

eqlv2

The official implementation of Equalization Loss v1 & v2 (CVPR 2020, 2021) based on MMDetection. https://arxiv.org/abs/2012.08548 https://arxiv.org/abs/2003.05176

fucking-algorithm

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

generative-recommenders

Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152, ICML'24).

GraphScope

GraphScope: A One-Stop Large-Scale Graph Computing System from Alibaba

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型

LaCLIP

[NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"

lazy

Lazy, a tool for running things in idle time

llama

Inference code for LLaMA models

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

PosterLayout-CVPR2023

Official repository for "PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout" (CVPR 2023).

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，Kenlm，Seq2Seq_Attention，BERT，MacBERT，ELECTRA，ERNIE，Transformer等模型实现，开箱即用。

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

Synonyms

:herb: 中文近义词：聊天机器人，智能问答工具包

tencent-ml-images

Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

tensorflow_cc

Build and install TensorFlow C++ API library.

the-algorithm

Source code for Twitter's Recommendation Algorithm

the-algorithm-ml

Source code for Twitter's Recommendation Algorithm

ULTRA

Unbiased Learning To Rank Algorithms (ULTRA)

Yi

A series of large language models trained from scratch by developers @01-ai