Featured Tool

Hugging Face TRL

Library for training LLMs with reinforcement learning (RLHF, DPO, PPO).

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

TRL, Transformer Reinforcement Learning by Hugging Face, is a library for post-training language models with techniques including supervised fine-tuning, reward modeling, PPO, GRPO, and Direct Preference Optimization. Built on the Transformers and PEFT ecosystem, it supports many architectures and modalities and scales across hardware with DeepSpeed and FSDP. Released under the Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
Apache-2.0
Minimum VRAM
8 GB
Added
Apr 3, 2026

Related Tools

Featured

Training scripts for Stable Diffusion fine-tuning with LoRA and DreamBooth.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

No-code tool by Hugging Face for training ML models automatically.

Open SourceSelf HostedOfflineGPU 8GB+
Beginner
0.0 (0)

All-in-one Stable Diffusion fine-tuning tool with intuitive GUI.

Open SourceSelf HostedOfflineGPU 8GB+
Easy
0.0 (0)
Featured

Parameter-efficient fine-tuning technique that adapts large models with minimal trainable parameters.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)

Library for post-training foundation models with SFT, DPO, GRPO, and other RL methods.

Open SourceSelf HostedOfflineGPU
Advanced
0.0 (0)

Efficient LLM quantization preserving important weight channels.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Browse all Model Training & Fine-Tuning tools