h2oai/h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

What it solves

H2O LLM Studio provides a no-code graphical user interface (GUI) and framework for fine-tuning large language models (LLMs). It removes the need for coding experience to perform complex fine-tuning tasks, allowing users to experiment with hyperparameters and advanced training techniques.

How it works

The tool allows users to upload datasets and create experiments to fine-tune LLMs. It supports both a GUI for intuitive management and a command-line interface (CLI) for advanced users. The framework integrates with NVIDIA GPUs and supports memory-efficient techniques like Low-Rank Adaptation (LoRA) and 8-bit training. For larger models, it utilizes DeepSpeed for sharded training across multiple GPUs.

Who it’s for

It is designed for users who want to fine-tune LLMs without writing code, as well as developers who need a visual way to track, compare, and evaluate model performance.

Highlights

  • No-Code GUI: A dedicated interface for managing the entire fine-tuning process.
  • Advanced Fine-Tuning: Supports LoRA, 8-bit training, and preference optimization techniques like DPO, IPO, and KTO.
  • Performance Tracking: Visual comparison of experiments and integration with Weights & Biases (W&B).
  • Model Export: Easy export of trained models to the Hugging Face Hub.
  • Flexible Deployment: Can be run via Docker, CLI, or cloud-based instances (e.g., RunPod).
  • Diverse Problem Types: Supports Causal Regression and Causal Classification modeling.

Related

  • Project
    hiyouga/LlamaFactory

    LlamaFactory is an open‑source toolkit that lets you fine‑tune, evaluate, and serve over 100 large language models with a simple YAML config, offering both a command‑line interface and a Gradio‑based web UI. It supports many modern training methods (LoRA, QLoRA, RLHF, PPO, DPO, etc.), a wide range of models (LLaMA‑3/4, Qwen 3, Mixtral‑MoE, Gemma 3, etc.), and runs on NVIDIA, AMD, Ascend NPU, or cloud services. Integrated monitoring (TensorBoard, WandB, SwanLab) and deployment options (OpenAI‑style API, vLLM/SGLang) make it suitable for researchers, product teams, and educators.

  • Dispatch
    Hugging Face Skills: Enabling AI Agents to Fine-Tune LLMs

    Hugging Face has introduced Hugging Face Skills, a tool that allows coding agents like Claude Code to manage the entire LLM fine-tuning lifecycle, from hardware selection to model deployment.

  • Dispatch
    Hugging Face Guide: Training a LLaMA 2 Chatbot Without Code

    Hugging Face provides a no-code workflow using Spaces, AutoTrain, and ChatUI to allow non-engineers to fine-tune LLaMA 2 and deploy it as a functional chat application.

  • Project
    unslothai/unsloth-zoo

    A utility library for Unsloth that enables faster and more memory-efficient fine-tuning of LLMs, vision, and TTS models with significantly reduced VRAM requirements.

  • Project
    OptimalScale/LMFlow

    LMFlow is an extensible Python toolbox for fine‑tuning large language models. It supports full‑parameter training, LoRA, the memory‑efficient LISA algorithm, QLoRA quantization, and a suite of speed‑up tricks (FlashAttention‑2, DeepSpeed, vLLM, SGLang). After training, it provides simple scripts for chat‑style inference and optional Gradio/Flask deployment. The library is designed for Linux/Colab environments and offers optional extras for multimodal models, distributed reward‑model inference, and more.