基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

comfyui-模特换装(Model dress up)

A Corpus for Chinese Literary Grace Evaluation(literary grace level, figure-of-speech, sentence category)

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

FAQ智能问答系统。实现FAQ的问题-模板匹配功能。部署轻量级的Web服务应用。

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

基于ChatGLM-6B + LoRA的Fintune方案

ChatGLM-6B-Slim：裁减掉20K图片Token的ChatGLM-6B，完全一样的性能，占用更小的显存。

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Code release for "TempLM: Distilling Language Models into Template-Based Generators"

Repository containing all source code and documentation of iLFQA: intelligent Longform Question Answering

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

基于ClipCap的看图说话Image Caption模型

Title and keywords are used to generate text.

sentence paraphrase

自然语言处理（NLP）教程，包括：词向量，词法分析，预训练语言模型，文本分类，文本语义匹配，信息抽取，翻译，对话。

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Question-answers, collected from Google

A flask-based Docker image providing a deep-learning long-form question answering service

基于飞桨开发的虚拟主播

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;

Code for ACL'20 paper "Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization" .

The official code for PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

Large-scale multi-document summarization dataset and code

Monolingual translation for paraphrasing tasks.