≫ Home / Fine-tuning / TRL

TRL

Hugging Face library for training language models with RLHF, SFT, and DPO

Open Source Free Trial

TRL (Transformer Reinforcement Learning) is the standard Hugging Face library for fine-tuning language models. It supports supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), direct preference optimization (DPO), and other alignment techniques. Built on top of Transformers and integrates with PEFT for parameter-efficient training.

Pricing: Free

Visit website →

Suggest changes

Screenshot of TRL webpage

TRL Alternatives

Explore 18 products in the Fine-tuning category. View all TRL alternatives.

LLaMA-Factory

Open-source fine-tuning framework for 100+ LLMs with a web UI

Ludwig

Declarative deep learning framework for building and fine-tuning models with YAML configuration

Lamini

Enterprise LLM fine-tuning platform with Memory Tuning for near-zero hallucination

Hugging Face

The open-source AI platform with 500K+ models, inference endpoints, and fine-tuning tools

torchtune

PyTorch-native library for fine-tuning LLMs on consumer and enterprise GPUs

Axolotl

Open-source toolkit for fine-tuning LLMs with a single YAML config across the full training pipeline

View all Fine-tuning tools ≫

Is your product missing? 👀 Add it here →