LLaVA Files

Visual Instruction Tuning: Large Language-and-Vision Assistant

This is an exact mirror of the LLaVA project, hosted at https://github.com/haotian-liu/LLaVA. SourceForge is not affiliated with LLaVA. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2023-10-26	812 Bytes	0
Release v1.1.3 (Bring your own data, LoRA training) source code.tar.gz	2023-10-26	13.2 MB	0
Release v1.1.3 (Bring your own data, LoRA training) source code.zip	2023-10-26	13.3 MB	0
Totals: 3 Items		26.5 MB	0

Updates

Support LoRA for the instruction tuning stage of LLaVA-1.5 -- comparable performance to full-model finetuning, and reduced requirements on GPU VRAM. (ckpts/logs, script)
Bring your own data and finetune LLaVA-1.5 to your own task. (instruction)
Basic support for Windows. (instruction)
Fix: the training behavior with gradient accumulation is the same as large-batch training.

Notes

A new LoRA schedule for LLaVA-1.5 is used,
rank: 128
alpha: 256
lr (LoRA): 2e-4
lr (projector): 2e-5

Source: README.md, updated 2023-10-26

Other Useful Business Software

Our Free Plans just got better! | Auth0

With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.

Try free now

Picsart Enterprise Background Removal API for Stunning eCommerce Visuals

Instantly remove the background from your images in just one click.

With our Remove Background API tool, you can access the transformative capabilities of automation , which will allow you to turn any photo asset into compelling product imagery. With elevated visuals quality on your digital platforms, you can captivate your audience, and therefore achieve higher engagement and sales.

Learn More

Recommended Projects

Accord.NET Framework
Machine learning, computer vision, statistics and computing for .NET
Clonezilla
A partition and disk imaging/cloning program
DeSmuME: Nintendo DS emulator
DeSmuME is a Nintendo DS emulator
Apache OpenOffice
The free and Open Source productivity suite
KeePass
A lightweight and easy-to-use password manager

LLaVA Files

Visual Instruction Tuning: Large Language-and-Vision Assistant

Get an email when there's a new version of LLaVA

Updates

Notes