# h2oai/h2o-llmstudio

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

Repository: https://github.com/h2oai/h2o-llmstudio
Canonical: https://ross.abutalabs.com/products/h2o-llmstudio
Homepage: https://h2o.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, chatbot, chatgpt, fine-tuning, finetuning, generative, generative-ai, gpt, llama, llama2, llm, llm-training, fedramp
Last push: 2026-08-18T14:26:40+00:00

## Health v2 (maintenance only)
Score: 96/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 98, longevity 88
- inputs: {"age_days": 1234, "days_push": 15, "days_rel": 15, "gap_med": 19.0, "n_releases_24m": 21}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5172, forks 555 (observed 2026-08-28T04:09:11.655117+00:00)

## What it is
H2O LLM Studio is a framework and no-code GUI for fine-tuning state-of-the-art large language models, built by H2O.ai. It supports LoRA and 8-bit low-memory training, RL-based fine-tuning, experiment tracking with W&B, model chat evaluation, and export to the Hugging Face Hub.

## Use cases
- fine-tune an LLM on custom instruction data without writing code
- apply LoRA or 8-bit training to fit large models on limited GPU memory
- compare and track fine-tuning experiments visually
- chat with a fine-tuned model to evaluate its answers
- export a fine-tuned model to the Hugging Face Hub
- run fine-tuning jobs from the command line or CI

## When to choose
- you want a GUI-driven, no-code workflow for LLM fine-tuning
- you need low-memory techniques like LoRA and 8-bit training
- you want built-in experiment tracking, evaluation, and chat testing
- you plan to publish models to the Hugging Face Hub

## When to avoid
- you need fully programmatic, scriptable training pipelines with custom training loops
- you are not working with LLMs (e.g., vision or tabular models)
- you lack GPU resources for training
- you need a lightweight library to embed in an existing ML stack rather than a standalone studio

## Facets
- artifact type: framework
- maturity: active
- function: llm-training, machine-learning, gui, cli, gpu-computing
- domain: large-language-models, machine-learning, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: fine-tuning, lora, no-code, huggingface, reinforcement-learning, wave-gui, wandb, docker, linux, gpu

## Member repositories
- h2oai/h2o-llmstudio (main) score 96

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.655117+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:01:51.382120+00:00, confidence not recorded.
  - readme: https://github.com/h2oai/h2o-llmstudio (fetched 2026-08-28T04:09:11.655117+00:00, sha 326850675118)
  - homepage: https://h2o.ai (fetched 2026-08-29T08:56:05.836461+00:00, sha 4bde7fae702d)
  - site_page: https://h2o.ai/docs (fetched 2026-08-29T08:56:05.860031+00:00, sha 411722578bc1)
  - site_page: https://h2o.ai/platform/enterprise-h2ogpte (fetched 2026-08-29T08:56:05.846918+00:00, sha 71f7b1d062f7)
  - site_page: https://h2o.ai/platform/why-h2o (fetched 2026-08-29T08:56:05.849733+00:00, sha dbfd58bb2a72)
  - site_page: https://h2o.ai/company (fetched 2026-08-29T08:56:05.851959+00:00, sha ddd0af08be22)
  - site_page: https://h2o.ai/company/press-media?tagFilter=Press+Release (fetched 2026-08-29T08:56:05.854142+00:00, sha 6aa60f9bcf14)
  - site_page: https://h2o.ai/partner-network/find-a-partner (fetched 2026-08-29T08:56:05.856798+00:00, sha 9d1a4050938e)
- Data as of 2026-08-30T08:39:29.467469+00:00.