Liadrinz/rllib-rlhf

Stars
3
Rank 3,946,236 (Top 79 %)
Language
Python
Created about 1 year ago
Updated about 1 year ago

Liadrinz/rllib-rlhf

Liadrinz

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

An RLlib implementation of Reinforcement Learning from Human Feedback (RLHF)

transformers-unilm

microsoft unilm-v1 compatible with huggingface transformers

transformers-copy-mechanism

Overwrite huggingface BART and GPT with copy mechanism

RLlib-Common-Paramters

RLlib超参数详解（中文）

qq-relation

QQ空间社交网络可视化

waibao-script

为特定的信息系统外包公司设计一款前端脚本语言, 充分考虑开发者的英语水平, 使开发者只需国内幼儿园英语水平即可进行前端开发, 极大降低前端开发的就业门槛。

tetris3d

3D俄罗斯方块 Tetris 3D

chicken-so-beautiful

HelloCUDA

Some classic parallel problems written with CUDA C++ and pycuda

beat_tracking

reward_shaping

jsonflow

A Crawling Framework Based on Data Flow and Decorators

MCDataStructure

Minecraft数据结构性能对比实验

django-graphql

django+graphql backend

volunteer-with-you

simple-knowledge-chatbot

homework-plus

homeworkplus project

MonkeyDocs

MonkeyDocs多人在线共享文字编辑器

Location

惯导行为识别模块

BR-MS

SimpleHBaseUtil

Homework of Hadoop