Fine Tune GPT Models Using Lit-Parrot by Lightening-AI

Author(s): Dr. Mandar Karhade, MD. PhD.

Originally published on Towards AI.

BYOD Bring Your Own Data! and Let's Train on Your GPU

Lit-Parrot is a hackable implementation of state-of-the-art open-source large language models:

StabilityAI StableLMEleutherAI PythiaTogether RedPajama-INCITETII UAE Falcon

Lit-Parrot has been released under the Apache 2.0 license.

This implementation builds on Lit-LLaMA and nanoGPT, and is powered by Lightning Fabric U+26A1.

Weights can be downloaded following these instructions:

StableLMPythiaRedpajama-INCITEFalcon

Lit-Parrot is:

Simple: Single-file implementation without boilerplate.Correct: Numerically equivalent to the original model.Optimized: Runs on consumer hardware or at scale.Open-source: No strings attached.

Clone the repo

git clone https://github.com/Lightning-AI/lit-parrotcd lit-parrot

Lit-Parrot currently relies on FlashAttention from PyTorch nightly. Until PyTorch 2.1 is released, you’ll need to install it nightly manually. Luckily that is straightforward:

On CUDA

# for cudapip install –index-url <https://download.pytorch.org/whl/nightly/cu118> –pre 'torch>=2.1.0dev'#… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI