In simple English
This tool helps you train artificial intelligence models on your own custom data. You do not need any coding experience to use its visual control panel. It runs on your own computer or server and keeps your data private. It requires a powerful graphics card to work properly. The software is free to use under an open-source licence.
What it is
H2O LLM Studio is a framework and no-code graphical user interface for fine-tuning large language models. It provides tools for dataset preparation, experiment tracking, model evaluation, and direct export to the Hugging Face Hub.
What it is good for
Solo builders who want to adapt an open-source language model for a specific task or domain without writing complex training scripts.
- Includes a visual web interface for managing training experiments.
- Supports modern memory-saving techniques like Low-Rank Adaptation and 8-bit training.
- Allows one-click export of trained models to the Hugging Face Hub.
- Requires a dedicated computer or cloud instance with a recent NVIDIA graphics card and at least 24 GB of memory.
- Rapid ongoing development can occasionally break backward compatibility between versions.
- Setup involves installing specific drivers, CUDA toolkits, and Python environment tools.
Writing custom PyTorch training scripts and manual experiment tracking.
Hugging Face Hub for sharing trained models.
- unslothai/unsloth78k stars
An alternative library focused on making large language model fine-tuning faster and more memory-efficient.
- axolotl-ai-cloud/axolotl13k stars
A popular configuration-driven tool for fine-tuning a wide variety of language models.
- ggml-org/llama.cpp132k stars
A C and C++ library and command-line tool for running language models locally.
- EleutherAI/lm-evaluation-harness14k stars
Runs standard question sets against a language model and reports the scores.
- mudler/LocalAI50k stars
Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.
git clone https://github.com/h2oai/h2o-llmstudio.git cd h2o-llmstudio make setup make llmstudio