Haoyu Song's repositories
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
awesome-sentiment-analysis
Reading list for Awesome Sentiment Analysis papers
ChatGPT
Reverse engineered ChatGPT API
chatgpt-api
Node.js client for the unofficial ChatGPT API. 🔥
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量
ClariQ
ClariQ: SCAI Workshop data challenge on conversational search clarification.
CLIP
Contrastive Language-Image Pretraining
CLUE
中文语言理解基准测评 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
CMAML
The implementation of "Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks"
DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
ESIM
Implementation of the ESIM model for natural language inference with PyTorch
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
fastRAG
Efficient Retrieval Augmentation and Generation Framework
image-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
llama
Inference code for LLaMA models
magma
MAGMA - a GPT-style multimodal model that can understand any combination of images and language
models
Pre-trained and Reproduced Deep Learning Models （『飞桨』官方模型库，包含多种学术前沿和工业场景验证的深度学习模型）
nlg-eval
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
NLP_ability
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力
paper-reading
深度学习经典、新论文逐段精读
perceiver-pytorch
Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
pet
This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"
simmc2
Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations
Task-Oriented-Dialogue-Dataset-Survey
A dataset survey about task-oriented dialogue, including recent datasets and SOTA results & papers.
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
vue-WeChat
:fire: 基于Vue2.0高仿微信App的单页应用