Train transformer language models with reinforcement learning.
☆19,194Sep 1, 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.☆21,618Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,236Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,967Aug 13, 2026Updated 2 weeks ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,755Jan 8, 2024Updated 2 years ago
- A modular RL library to fine-tune language models to human preferences☆2,395Mar 1, 2024Updated 2 years 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.
- Fast and memory-efficient exact attention☆24,827Updated this week
- Fully open reproduction of DeepSeek-R1☆26,446Apr 2, 2026Updated 5 months ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆74,501Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆43,049Updated this week
- Robust recipes to align language models with human and AI preferences☆5,669May 26, 2026Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆90,690Updated this week
- Ongoing research training transformer models at scale☆17,699Updated this week
- A framework for few-shot evaluation of language models.☆13,856Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,524May 1, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Large Language Model Text Generation Inference☆10,889Mar 21, 2026Updated 5 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,907Aug 11, 2024Updated 2 years ago
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,840Updated this week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,245Jul 17, 2024Updated 2 years ago
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆25,010Aug 12, 2024Updated 2 years ago
- Example models using DeepSpeed☆6,845Aug 26, 2026Updated last week
- QLoRA: Efficient Finetuning of Quantized LLMs☆11,003Jun 10, 2024Updated 2 years ago
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆15,478Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆33,045Updated this week
- 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.
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆22,200Aug 26, 2026Updated last week
- 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal model…☆164,700Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,452Updated this week
- Inference code for Llama models☆59,586Jan 26, 2025Updated last year
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,422May 20, 2026Updated 3 months ago
- Instruct-tune LLaMA on consumer hardware☆18,910Jul 29, 2024Updated 2 years ago
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.☆75,423Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,811Aug 24, 2026Updated last week
- slime is an LLM post-training framework for RL Scaling.☆8,340Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Tools for merging pretrained large language models.☆7,327Jun 17, 2026Updated 2 months ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,609Mar 27, 2023Updated 3 years ago
- Simple RL training for reasoning☆3,874Dec 23, 2025Updated 8 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆5,139Updated this week
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,391Jul 25, 2023Updated 3 years ago
- Making large AI models cheaper, faster and more accessible☆41,448Updated this 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…☆18,556May 19, 2026Updated 3 months ago