2,002 offers
Free Fine-Tuning — open-source & self-hostable
Training, fine-tuning, and dataset tooling
Scores rate free-tier value on a 1–10 scale. How scores work →
-
Unsloth Fine-Tuning 8.3 Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. 67.8k★1.1k/90d29 devs/90d -
LLaMA-Factory Fine-Tuning 7.7 Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) 72.9k★67/90d33 devs/90d -
DeepSpeed Fine-Tuning 7.7 DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. 42.6k★97/90d41 devs/90d -
Megatron-LM Fine-Tuning 7.7 Ongoing research training transformer models at scale 16.9k★617/90d32 devs/90d -
verl Fine-Tuning 7.6 verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework 22.3k★404/90d65 devs/90d -
TRL Fine-Tuning 7.6 Train transformer language models with reinforcement learning. 18.8k★490/90d15 devs/90d -
PEFT Fine-Tuning 7.5 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. 21.4k★138/90d38 devs/90d -
ms-swift (SWIFT) Fine-Tuning 7.3 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, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025). 14.7k★308/90d17 devs/90d -
TorchTitan Fine-Tuning 7.1 A PyTorch native platform for training generative AI models 5.5k★518/90d25 devs/90d -
Axolotl Fine-Tuning 7.0 Go ahead and axolotl questions 12.1k★131/90d15 devs/90d -
Oumi Fine-Tuning 6.8 Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM! 9.3k★128/90d18 devs/90d -
slime Fine-Tuning 6.8 slime is an LLM post-training framework for RL Scaling. 7.3k★174/90d22 devs/90d -
XTuner Fine-Tuning 6.8 A Next-Generation Training Engine Built for Ultra-Large MoE Models 5.2k★287/90d16 devs/90d -
Verifiers Fine-Tuning 6.8 Our library for RL environments + evals 4.3k★574/90d8 devs/90d -
Ludwig Fine-Tuning 6.7 Low-code framework for building custom LLMs, neural networks, and other AI models 11.7k★206/90d2 devs/90d -
OpenPipe ART Fine-Tuning 6.7 Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more! 10.2k★95/90d10 devs/90d -
AReaL Fine-Tuning 6.7 The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible. 5.5k★166/90d29 devs/90d -
LitGPT Fine-Tuning 6.6 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale. 13.5k★21/90d8 devs/90d -
Liger Kernel Fine-Tuning 6.6 Efficient Triton Kernels for LLM Training 6.5k★68/90d23 devs/90d -
MLX-LM Fine-Tuning 6.4 Run LLMs with MLX 6.2k★34/90d24 devs/90d -
Open-Instruct Fine-Tuning 6.4 AllenAI's post-training codebase 3.8k★94/90d12 devs/90d -
SkyRL Fine-Tuning 6.4 SkyRL: A Modular Full-stack RL Library for LLMs 2k★225/90d19 devs/90d -
prime-rl Fine-Tuning 6.4 Agentic RL Training at Scale 1.6k★354/90d18 devs/90d -
OpenRLHF Fine-Tuning 6.3 An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL) 9.7k★30/90d5 devs/90d -
Colossal-AI Fine-Tuning 6.1 Making large AI models cheaper, faster and more accessible 41.4k★3/90d1 devs/90d -
H2O LLM Studio Fine-Tuning 6.1 H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/ 5k★28/90d4 devs/90d -
EleutherAI GPT-NeoX Fine-Tuning 5.8 An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries 7.4k★7/90d3 devs/90d -
LMFlow Fine-Tuning 5.7 An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All. 8.5k★9/90d3 devs/90d -
torchtune Fine-Tuning 5.4 PyTorch native post-training library 5.8k★2/90d2 devs/90d -
AutoTrain Advanced Fine-Tuning 5.3 🤗 AutoTrain Advanced 4.6k★2/90d2 devs/90d -
nanoGPT Fine-Tuning 5.2 The simplest, fastest repository for training/finetuning medium-sized GPTs. 60.5k★0/90d0 devs/90d -
RAGEN Fine-Tuning 5.1 RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments. 2.7k★10/90d2 devs/90d -
Distilabel Fine-Tuning 4.7 Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers. 3.3k★0/90d0 devs/90d -
trlX Fine-Tuning 3.9 A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF) 4.8k★0/90d0 devs/90d -
Levanter Fine-Tuning 3.9 Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax 706★0/90d0 devs/90d -
rLLM Fine-Tuning 3.0 Agentica's framework for post-training language agents with RL, used to train reasoning and coding agents like DeepCoder. 400★0/90d0 devs/90d