Train transformer language models with reinforcement learning.
☆18,701Jun 24, 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.☆21,299Updated this week
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,673Jun 17, 2026Updated last week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,749Jan 8, 2024Updated 2 years ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,070Updated this week
- A modular RL library to fine-tune language models to human preferences☆2,389Mar 1, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆83,677Updated this week
- Fast and memory-efficient exact attention☆24,221Updated this week
- Fully open reproduction of DeepSeek-R1☆26,329Apr 2, 2026Updated 2 months ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆72,482Updated this week
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆42,544Jun 18, 2026Updated last week
- Robust recipes to align language models with human and AI preferences☆5,614May 26, 2026Updated 3 weeks ago
- Ongoing research training transformer models at scale☆16,761Updated this week
- A framework for few-shot evaluation of language models.☆13,024Jun 2, 2026Updated 3 weeks ago
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆39,486May 1, 2026Updated last month
- 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☆10,863Mar 21, 2026Updated 3 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,887Aug 11, 2024Updated last year
- SGLang is a high-performance serving framework for large language models and multimodal models.☆29,460Updated this week
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆9,737Updated this week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆30,249Jul 17, 2024Updated last year
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,881Aug 12, 2024Updated last year
- Example models using DeepSpeed☆6,823May 20, 2026Updated last month
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,933Jun 10, 2024Updated 2 years ago
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆22,151Jan 23, 2026Updated 5 months 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.
- 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal model…☆161,885Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,286Updated this week
- Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.☆67,133Updated this week
- Inference code for Llama models☆59,461Jan 26, 2025Updated last year
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,393May 20, 2026Updated last month
- Instruct-tune LLaMA on consumer hardware☆18,913Jul 29, 2024Updated last year
- Tools for merging pretrained large language models.☆7,173Jun 17, 2026Updated last week
- Simple RL training for reasoning☆3,865Dec 23, 2025Updated 6 months ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,598Mar 27, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for the paper Fine-Tuning Language Models from Human Preferences☆1,394Jul 25, 2023Updated 2 years ago
- Go ahead and axolotl questions☆12,082Updated this week
- Making large AI models cheaper, faster and more accessible☆41,404May 25, 2026Updated last month
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆18,378May 19, 2026Updated last month
- Minimal reproduction of DeepSeek R1-Zero☆13,174Feb 27, 2026Updated 3 months ago
- AllenAI's post-training codebase☆3,759Updated this week
- 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…☆14,561Jun 18, 2026Updated last week