# lxe/simple-llm-finetuner

Simple UI for LLM Model Finetuning

Repository: https://github.com/lxe/simple-llm-finetuner
Canonical: https://ross.abutalabs.com/products/simple-llm-finetuner
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: ai, gpt-2, gpt-3, huggingface, huggingface-transformers, llama, llm, peft, pytorch
Last push: 2023-12-21T21:42:03+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 90
- inputs: {"age_days": 1260, "days_push": 986, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2054, forks 131 (observed 2026-08-28T04:06:09.776437+00:00)

## What it is
A beginner-friendly Gradio web UI for fine-tuning LLMs (LLaMA, GPT-2) using LoRA via the Hugging Face PEFT library on consumer NVIDIA GPUs. It lets users paste datasets, adjust training parameters, and run inference from the browser.

## Use cases
- fine-tune llama on my own dataset with a simple ui
- train a language model with lora on a single gpu
- beginner-friendly llm finetuning tool
- run peft finetuning in google colab
- customize an llm with a small training dataset

## When to choose
- you want a minimal, no-code UI to experiment with LoRA fine-tuning on a 16GB GPU or Colab T4

## When to avoid
- the project is explicitly dead and unmaintained - use LLaMA-Factory, unsloth, or text-generation-webui instead
- you need production-grade or actively supported fine-tuning workflows
- you lack an NVIDIA GPU or WSL/Linux environment

## Facets
- artifact type: application
- maturity: abandoned
- function: llm-training, machine-learning, gui
- domain: large-language-models, machine-learning, artificial-intelligence
- platform: python
- tags: llm-finetuning, lora, peft, gradio, huggingface, colab, beginner-friendly, linux, gpu, web-server

## Member repositories
- lxe/simple-llm-finetuner (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.776437+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 2026-08-30T02:57:18.221129+00:00, confidence not recorded.
  - readme: https://github.com/lxe/simple-llm-finetuner (fetched 2026-08-28T04:06:09.776437+00:00, sha 28bb797edc00)
- Data as of 2026-08-30T08:39:29.467469+00:00.