Pinned Repositories
aft-pytorch
Unofficial PyTorch implementation of **Attention Free Transformer**'s layers by [Zhai](https://twitter.com/zhaisf?lang=en), et al. [[abs](https://openreview.net/forum?id=pW--cu2FCHY), [pdf](https://arxiv.org/pdf/2105.14103.pdf)] from Apple Inc.
CAIL
**法研杯-司法人工智能挑战赛(CAIL2018-2020)
Chinese-PreTrained-BERT
We released BERT-wwm, a Chinese pre-training model based on Whole Word Masking technology, and models closely related to this technology. 我们发布了基于全词遮罩（Whole Word Masking）技术的中文预训练模型BERT-wwm，以及与此技术密切相关的模型
Chinese-PreTrained-GPT
我们发布了基于Generative Pre-Training技术的中文预训练模型CP-GPT，以及与此技术密切相关的模型
Chinese-PreTrained-XLNet
本项目提供了面向中文的XLNet预训练模型，旨在丰富中文自然语言处理资源，提供多元化的中文预训练模型选择。 我们欢迎各位专家学者下载使用，并共同促进和发展中文资源建设。
icme2019
短视频内容理解与推荐竞赛
lawa
“法阿”中文分词：做最好的 Python 法律中文分词组件
lawaplugin
lawa-plugin是Elasticsearch的中文分词插件，后端模型是由法律法规、案例、期刊语料统计而成，并具有新词发现功能。
Open-Prompt-Research
Some thoughts on prompts for Large Language Models.
rct-intel-hw-recommend
2021微信大数据挑战赛
ShenDezhou's Repositories
ShenDezhou/CAIL
**法研杯-司法人工智能挑战赛(CAIL2018-2020)
ShenDezhou/Chinese-PreTrained-BERT
We released BERT-wwm, a Chinese pre-training model based on Whole Word Masking technology, and models closely related to this technology. 我们发布了基于全词遮罩（Whole Word Masking）技术的中文预训练模型BERT-wwm，以及与此技术密切相关的模型
ShenDezhou/Chinese-PreTrained-XLNet
本项目提供了面向中文的XLNet预训练模型，旨在丰富中文自然语言处理资源，提供多元化的中文预训练模型选择。 我们欢迎各位专家学者下载使用，并共同促进和发展中文资源建设。
ShenDezhou/Open-Prompt-Research
Some thoughts on prompts for Large Language Models.
ShenDezhou/Open-GPT
GPT is a belief. This project provides a code library for efficiently training Chinese GPT. This project uses the nanoGPT framework and the novel optimizer algorithm sophia.
ShenDezhou/OpenAI-Tech-Research
A project following OpenAI's cutting edge technology
ShenDezhou/academic
A site of self introduction in acdemic.
ShenDezhou/APSP
An algorithm to calculate All Paires Shortest Path efficiently.
ShenDezhou/LSTM
A LSTM based Chinese Segment Project.
ShenDezhou/Open-BERT-IR
Open BERT rank pretrained models.
ShenDezhou/Open-Chinese-Tokenization
An open Chinese language byte piece encoding tokenization models.
ShenDezhou/Open-Transformer
An open transformer project with T5-style architecture.
ShenDezhou/Chinese-PreTrained-GPT
我们发布了基于Generative Pre-Training技术的中文预训练模型CP-GPT，以及与此技术密切相关的模型
ShenDezhou/thunet
A transformer deep learning net "TsingHua University transformers NET", with a short name 'thunet'.
ShenDezhou/thunet-tutorial
A beginners' tutorial for building deep learning models from scratch without the help of pytorch and tensorflow.
ShenDezhou/avengers
A collection of super hero models with larger than 90 scores in SST-2 task. Just like The Avengers!
ShenDezhou/Chinese-DuckDB
A project to navigate Chinese Datasets on Hugging Face.
ShenDezhou/Chinese-LLM-Collector
An LLM based Chinese datasets collector.
ShenDezhou/cv-attention
A simple Vision Transformers.
ShenDezhou/cv-coco-annotator
ShenDezhou/ELMo2
ShenDezhou/ELMos
ShenDezhou/Jacob-Devlin-bert
ShenDezhou/MineCraft-Server
A document for diffrent MineCarft servers.
ShenDezhou/Mixtral-Tokenizer
Train a Mistral/Mixtral Tokenizer.
ShenDezhou/Open-ALBERT-Pre-Training
An Open ALBERT project for Chinese Language.
ShenDezhou/Open-BERT
BERT is a belief.
ShenDezhou/Open-Node-Research
A light API to control Minecraft agents: to start an agent, to evaluate a piece of code, to end an agent, to pause an agent.
ShenDezhou/Open-Pre-Training-BERT
To pre-train an Open BERT.
ShenDezhou/thu-vision-net