Young1993

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

gpt4all

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

pytorch-lightning

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

flux

Official inference repo for FLUX.1 models

FinGPT

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

sglang

SGLang is a fast serving framework for large language models and vision language models.

ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

mteb

MTEB: Massive Text Embedding Benchmark

instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Restormer

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

CogView

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Research

novel deep learning research works with PaddlePaddle

CrossWOZ

A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

CPT

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

picard

PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models. PICARD is a ServiceNow Research project that was started at Element AI.

PLOME

Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021

SPN4RE

text2image_safety

backpacks-flash-attn

The original Backpack Language Model implementation, a fork of FlashAttention

g2g-transformer

Pytorch implementation of “Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement”

G2GTr

Pytorch implementation of Graph-to-Graph Transformer for Transition-based Dependency Parsing accepted to EMNLP 2020

UGEN

Incorporating Instructional Prompts into A Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling - Coling2022(Oral))

tlm

The public code of EMNLP2023 (main conference) paper "TLM: Token-Level Masking for Transformers"

s2a4gec