LLM-Finetuning provides PEFT-based fine-tuning tutorials and Colab notebooks for LoRA and related methods, using Hugging Face transformers. It lists 2970 stars and 768 forks as of dataset, with activity last pushed 2025-08-01.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
LLM-Finetuning is a PEFT fine-tuning project focusing on efficient training of large language models using LoRA and Hugging Face's transformers library. The repository includes a collection of notebooks, each detailing procedures to fine-tune models such as LLaMA-2, BLOOM, Falcon, and others via PEFT methods.
How it works
The project centers on fine-tuning large language models with parameter-efficient techniques (LoRA) implemented through Hugging Face transformers and the PEFT library. The README showcases a notebook table with titles describing efficient training, fine-tuning on Colab, and various model-specific tutorials. The notebooks are designed to be run in Colab and linked from the repository.
Getting started
Getting started information is limited to the presence of a notebook table in the README, with Colab links for each notebook. The exact usage commands are not provided in the truncated README excerpt. The repository language is Jupyter Notebook and there is no license listed.
Recent releases
There are no releases listed for the latest version (latest 0: none).
Traction
Stars: 2970 • Forks: 768 • Open issues: 3
Behind the repo
No startup/company link is provided in the FACTS block.
Caveats
License: none listed Created: 2023-06-08 Last push: 2025-08-01