Starred repositories
Summarize existing representative LLMs text datasets.
Let your Claude able to think
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
gevtushenko / llm.c
Forked from karpathy/llm.cLLM training in simple, raw C/CUDA
A project to improve skills of large language models
EasyTPP: Towards Open Benchmarking Temporal Point Processes
去广告magisk模块,通过DNS层面过滤广告、防DNS劫持,使用前请先详读mode.conf文件,使用前需关闭私人dns,不可用wap接入点,支持订阅过滤规则,可兼容VPN、免模块、翻模块、校园网等特殊使用环境。top大佬(酷安)
Downloads videos and playlists from YouTube
ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate
Fast and memory-efficient exact attention
Source code for article https://paul.pub/a-star-algorithm
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Solving a Rubik's Cube and 15 Puzzle using the Deep Reinforcement Learning and Search
Code for DeepCubeA, a Deep Reinforcement Learning algorithm that can learn to solve the Rubik's cube.
[WWW'2023] "MMSSL: Multi-Modal Self-Supervised Learning for Recommendation"
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Solving Rubik's Cube with Deep Reinforcement Learning, A* and visualize with PyQt5.
The official code of our paper at EMNLP 2022: Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
哔哩下载姬downkyi,哔哩哔哩网站视频下载工具,支持批量下载,支持8K、HDR、杜比视界,提供工具箱(音视频提取、去水印等)。
My coursework for Machine Learning (2021 Spring) at National Taiwan University (NTU)