RLHF中文手册 - 详细解析RLHF全流程优化阶段,涵盖指令调优、奖励模型训练,以及拒绝采样、强化学习和直接对齐算法等关键技术。
☆64Sep 20, 2026Updated 2 months ago
Alternatives and similar repositories for RLHF-book-Chinese
Users that are interested in RLHF-book-Chinese are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A minimal hackable implementation of policy gradient methods (GRPO, PPO, REINFORCE)☆18Feb 20, 2026Updated 9 months ago
- Textbook on reinforcement learning from human feedback☆2,540Updated this week
- Evaluating language models on word puzzle games☆10Oct 25, 2024Updated 2 years ago
- ☆19Oct 2, 2023Updated 3 years ago
- [COLM 2026] Official codebase of paper "Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Followi…☆13Nov 5, 2026Updated 2 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Stock prediction using RWKV NN. Until now most of the usage done with RWKV was for LM.☆12Jul 3, 2023Updated 3 years ago
- Demonstration of MoE distributed training using various techniques☆11Oct 31, 2024Updated 2 years ago
- ☆11Dec 29, 2023Updated 2 years ago
- 对llava官方代码的一些学习笔记☆28Oct 11, 2024Updated 2 years ago
- Source code and additional results for GLOD issues☆12Jan 19, 2023Updated 3 years ago
- 可以成功Lora微调的Qwen-VL模型☆16Oct 27, 2023Updated 3 years ago
- 上下文工程(中文版)☆51Oct 7, 2025Updated last year
- 神机是一个专门针对网络安全领域的AI大模型训练系统,默认基于qwen2大模型进行LoRA微调。由云霖网络安全实验室开发,采用模块化架构设计,具备完整的身份认知和专业的网络安全知识体系。☆12Jul 18, 2025Updated last year
- 想看下你的思维净活跃时长吗?☆34Nov 7, 2026Updated last week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Source Code for Graph Anomaly Detection with Unsupervised GNNs (ICDM2022)☆11Oct 18, 2022Updated 4 years ago
- Fine-tuning Vision Language Model (Qwen2.5-VL-7B) with Hugging Face TRL - Tutorial and implementation for visual question-answering on Ch…☆10Updated this week
- Official code for infimm-hd☆16Sep 4, 2024Updated 2 years ago
- An LLM post-training framework with vLLM for RL Scaling☆506Updated this week
- The collections of MOE (Mixture Of Expert) papers, code and tools, etc.☆12Mar 15, 2024Updated 2 years ago
- 一个用于共享《Mathematical Foundations of Reinforcement Learning》的中文翻译版本的仓库☆20Dec 26, 2025Updated 10 months ago
- 从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。☆223Oct 21, 2026Updated last month
- This is a project designed for tts, based on the minimind codebase.☆13Feb 10, 2025Updated last year
- 实时数字人☆13Nov 4, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- This repository contains data, code and models for contextual noncompliance.☆26Jul 18, 2024Updated 2 years ago
- An example "getting started" python project based on `uv`☆18Nov 2, 2026Updated 2 weeks ago
- Collection of LLM completions for reasoning-gym task datasets☆32Jul 4, 2025Updated last year
- 一个基于保险QA以及合同条款的RAG业务链,使用了Qwen的api作为语言模型,其中还包括了分类算法(意图识别)的训练, RAG embedding模型的微调, 稠密稀疏indexing的建立和混合使用☆12Jun 12, 2024Updated 2 years ago
- Notebook - Fine-tuning Vision-Language Models (VLMs) on custom datasets☆11Feb 9, 2025Updated last year
- A dispatcher based on Hashicorp's Raft for Casbin.☆17May 15, 2026Updated 6 months ago
- Official implementation of "On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning"☆14Oct 13, 2022Updated 4 years ago
- Custom Behaviour Planning module for Apollo Auto based on hierarchical Behaviour Trees☆10May 20, 2021Updated 5 years ago
- ☆13Sep 22, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Native macOS text-to-speech app powered by Qwen3-TTS and Apple Silicon (MLX). Voice cloning, voice design, and custom voices — all runnin…☆14Feb 8, 2026Updated 9 months ago
- verl Ascend specific recipe☆24Updated this week
- 💥 Tiny 9M MoEs with Dynamic Routing☆13May 29, 2024Updated 2 years ago
- This is the source code of paper CollaboVR: A Reconfigurable Framework for Creative Collaboration in Virtual Reality https://ieeexplore.i…☆13Jul 24, 2021Updated 5 years ago
- https://github.com/orgs/autowarefoundation/discussions/5033☆11Feb 20, 2026Updated 9 months ago
- ☆17Oct 21, 2026Updated 3 weeks ago
- A course for Mao Yisheng College of SWJTU☆11Mar 28, 2020Updated 6 years ago
Are these results useful?