h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
What is h2o-llmstudio?
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
Overview of h2o-llmstudio
What it is
H2O LLM Studio is a framework and no-code GUI for fine-tuning large language models (LLMs). It is designed to allow users to fine-tune state-of-the-art LLMs without any coding experience. The project is open source under the Apache-2.0 license and is hosted on GitHub at https://github.com/h2oai/h2o-llmstudio. Documentation is available at https://docs.h2o.ai/h2o-llmstudio/. The project is categorized under AI and is free to use.
Key features
- Graphical user interface (GUI) specially designed for large language models.
- Fine-tune any LLM using a large variety of hyperparameters.
- Use recent fine-tuning techniques such as Low-Rank Adaptation (LoRA) and 8-bit model training with a low memory footprint.
- Use Reinforcement Learning (RL) to fine-tune your model (experimental).
- Use advanced evaluation metrics to judge generated answers by the model.
- Track and compare your model performance visually.
- Chat with your model and get instant feedback on your model performance.
- Easily export your model to the Hugging Face Hub and share it with the community.
Use cases
H2O LLM Studio can be used for fine-tuning large language models for various natural language processing tasks. It supports causal classification modeling for binary and multiclass models, causal regression modeling for single target regression data, and DPO/IPO/KTO optimization as an alternative to RLHF. The framework is suitable for users who want to fine-tune LLMs without coding, as well as for those who prefer a command line interface for scripting and automation.
Getting started
The recommended way to install H2O LLM Studio is using uv with Python 3.12. To set up the environment, run:bashmake setupTo start the GUI, run:bashmake llmstudioNavigate to http://localhost:10101 to access H2O LLM Studio. For Docker usage, pull the image and run the container as described in the repository README. For CLI usage, use:bashuv run python llm_studio/train.py -Y {path_to_config_yaml_file}
License and pricing
The project is licensed under Apache-2.0 and is open source. Pricing is not stated; the project is categorized as open source.
Based on the project's public README and repository metadata.