Train transformer language models with reinforcement learning.
☆18,134Apr 22, 2026Updated this week
Alternatives and similar repositories for trl
Users that are interested in trl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆20,981Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,381Apr 19, 2026Updated last week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,745Jan 8, 2024Updated 2 years ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆20,930Updated this week
- A modular RL library to fine-tune language models to human preferences☆2,387Mar 1, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆77,531Updated this week
- Fast and memory-efficient exact attention☆23,457Updated this week
- Fully open reproduction of DeepSeek-R1☆26,004Apr 2, 2026Updated 3 weeks ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆70,504Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆42,188Updated this week
- Robust recipes to align language models with human and AI preferences☆5,572Apr 8, 2026Updated 2 weeks ago
- Ongoing research training transformer models at scale☆16,145Updated this week
- A framework for few-shot evaluation of language models.☆12,331Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,451Jun 2, 2025Updated 10 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Large Language Model Text Generation Inference☆10,843Mar 21, 2026Updated last month
- SGLang is a high-performance serving framework for large language models and multimodal models.☆26,397Updated this week
- Reference implementation for DPO (Direct Preference Optimization)☆2,884Aug 11, 2024Updated last year
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,621Apr 17, 2026Updated last week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,259Jul 17, 2024Updated last year
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,707Aug 12, 2024Updated last year
- Example models using DeepSpeed☆6,819Mar 30, 2026Updated 3 weeks ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,892Jun 10, 2024Updated last year
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆22,107Jan 23, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal model…☆159,742Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,149Updated this week
- Web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.☆62,269Updated this week
- Inference code for Llama models☆59,370Jan 26, 2025Updated last year
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,352Dec 9, 2025Updated 4 months ago
- Instruct-tune LLaMA on consumer hardware☆18,945Jul 29, 2024Updated last year
- Tools for merging pretrained large language models.☆7,023Mar 15, 2026Updated last month
- Simple RL training for reasoning☆3,849Dec 23, 2025Updated 4 months ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,591Mar 27, 2023Updated 3 years ago
- 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.
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,387Jul 25, 2023Updated 2 years ago
- Go ahead and axolotl questions☆11,737Updated this week
- Making large AI models cheaper, faster and more accessible☆41,375Apr 13, 2026Updated last week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆18,300Updated this week
- Minimal reproduction of DeepSeek R1-Zero☆13,070Feb 27, 2026Updated 2 months ago
- AllenAI's post-training codebase☆3,702Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆13,898Updated this week