trl

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach

Agentic RL 中文零基础教程（33 章）：从概念到 GRPO 实战，含 TRL 最小可跑示例；26–33 章附一套可运行的三方判别模型实证工程（encoder vs LLM-LoRA vs 规则基线）。第 25 章讲清 Jev / TypeSafe System One 与 RL 的能力边界 | Chinese Agentic RL tutorial (33 chapters) + a reproducible discriminative-model benchmark

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

An implementation of GRPO for Unsloth's VLMs training

基于DPO算法微调语言大模型，简单好上手。

Code repository dedicated to experimenting and research with tiny reasoning language model

Various training, inference and validation code and results related to Open LLM's that were pretrained (full or partially) on the Dutch language.

simpleR1: A Simple Framework for Training R1-like Models

realize the reinforcement learning training for gpt2 llama bloom and so on llm model

This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.

An open-source application that estimates an Open Source Software Technology Readiness Level (OSSTRL) 1–9 from evidence that can be gathered automatically from a GitHub repository.

Training-data memorization auditor for fine-tuned LLMs — Trainer/TRL plugin, canary MIA + regurgitation audit, Apache-2.0

Build task models that replace frontier API calls

使用trl、peft、transformers等库，实现对huggingface上模型的微调。

Different post-training techniques for LLMs, including: SFT, DPO and Online RL

Vibe Innovation und Vibe Coding Workshop mit GitHub Codespaces

Config-driven LLM fine-tuning with safety evaluation, EU AI Act compliance, 6 alignment methods, and one-command bundled quickstart templates.