Desein-Yang
Pretrained Language Model / Deep Reinforcement Learning / Evolutionary Computation
Shenzhen, China
Pinned Repositories
awesome-graph-structure-learning
A curated list of amazingly awesome things regarding Graph Structure Learning.
BookScraper
An easy web scraper framework to crawl book and other web(childbook, novel, knowledge, qa etc).
CirclePack
Circle Pack Problem Solver
Course-Adavance-Algorithms
Handcraft Implements of some algorithms learned in master course "Advanced Algorithm" &"Advanced Articficial Intelligence"
Light-ML-Demo
A light and fast demo with streamlit as frontend and fastapi as backend. Get started from it and quickly build a demo for your Machine Learning application.
LoRA_Lightning
Implementation of Finetuning Bert Low-rank Matrix (LoRa) with Gradient Optimizer & Evolution Strategy Optimizer.
NCNES
This repository is an implement of Negative correlated natural gradient strategy (https://link.springer.com/article/10.1007/s11704-020-0431-0), which is an advancement natural evolution strategy under negative correlated search framework.
NCS-RL
The Implementation of Reinforcement Learning Algorithms with Negatively correlated search framework. It contains four algorithms: NCS-C, NCSCC, NCSRE, NCNES. It based on OpenAI CES API and details will be showed on the readme.md.
RLES
Evolution strategy as an optimizer in Deep Reinforcement learning
Fengshenbang-LM
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
Desein-Yang's Repositories
Desein-Yang/NCS-RL
The Implementation of Reinforcement Learning Algorithms with Negatively correlated search framework. It contains four algorithms: NCS-C, NCSCC, NCSRE, NCNES. It based on OpenAI CES API and details will be showed on the readme.md.
Desein-Yang/LoRA_Lightning
Implementation of Finetuning Bert Low-rank Matrix (LoRa) with Gradient Optimizer & Evolution Strategy Optimizer.
Desein-Yang/awesome-graph-structure-learning
A curated list of amazingly awesome things regarding Graph Structure Learning.
Desein-Yang/NCNES
This repository is an implement of Negative correlated natural gradient strategy (https://link.springer.com/article/10.1007/s11704-020-0431-0), which is an advancement natural evolution strategy under negative correlated search framework.
Desein-Yang/RLES
Evolution strategy as an optimizer in Deep Reinforcement learning
Desein-Yang/BookScraper
An easy web scraper framework to crawl book and other web(childbook, novel, knowledge, qa etc).
Desein-Yang/CirclePack
Circle Pack Problem Solver
Desein-Yang/Course-Adavance-Algorithms
Handcraft Implements of some algorithms learned in master course "Advanced Algorithm" &"Advanced Articficial Intelligence"
Desein-Yang/Desein-Yang.github.io
CV page
Desein-Yang/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Desein-Yang/FastDemo-Template
A fast demo for datasets and large language model with Streamlit (python repo).
Desein-Yang/GARL
Code for the paper "Generative Adversarial Reinforcement Learning"
Desein-Yang/KindleNotes
Manage and reorganize your Kindle highlight , notes and bookmarks with python. Support output md and category by title, author, tag or nation.
Desein-Yang/Light-ML-Demo
A light and fast demo with streamlit as frontend and fastapi as backend. Get started from it and quickly build a demo for your Machine Learning application.
Desein-Yang/RL-LearnFromDemo
A Reproduction of Imitated Reinforcement Learning from Human Demonstration.
Desein-Yang/Snippet-Reporsitory
Some repeated used snippets and notes in python project.
Desein-Yang/typora-theme-backup
a backup of my theme
Desein-Yang/LangChain
⚡ Building applications with LLMs through composability ⚡
Desein-Yang/lm_dataformat
fix some bug of lmd
Desein-Yang/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Desein-Yang/lora-training
LoRA training model packaged with Cog