Wei He's repositories
AlphaTaiBai
以文搜诗,以图搜诗 - 不必再局限于关键字匹配,而是根据语义和语境排序返回结果.
ReadingClub
This is the code base of our Weekend Reading Club.
summary-consistency
Summary Consitency Detection (Summary Consistency/hallucinations/Factuall Error)
CrowdSourcing
A simple e2e crowd source solution, anyone can contribute to it from WeChat mini program, anyone can publish it's task.
GPT-Catch-Up-from-China-100-days
A personal developer located in China, what' the roadmap looks like to catch up the milestones of GPT evolution in future 100 days
SemanticTextualUnits
partition the web document into semantic Textual Units
tensorflow-seq2seq-tutorials
Dynamic seq2seq in TensorFlow, step by step
attention-networks-for-classification
Hierarchical Attention Networks for Document Classification in PyTorch
azure-event-hubs-go
Golang client library for Azure Event Hubs https://azure.microsoft.com/services/event-hubs
Chinese-alpaca-lora
骆驼:A Chinese finetuned instruction LLaMA. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)
Chinese-LLaMA-Alpaca-2
中文 LLaMA-2 & Alpaca-2 大模型二期项目 + 本地CPU/GPU训练部署 (Chinese LLaMA-2 & Alpaca-2 LLMs)
finetune-transformer-lm
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
image_showcases
for images show cases usage
pytorch-openai-transformer-lm
A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
web_doc_summarization
try to summarize web documents syntactically and semantically