After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co/docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team

28 replies

liked a model 28 days ago

Qwen/Qwen2.5-14B-Instruct-AWQ

Text Generation • Updated Oct 9, 2024 • 25.8k • 13

liked a model 30 days ago

Qwen/Qwen2.5-32B-Instruct-AWQ

Text Generation • Updated Oct 9, 2024 • 22.8k • 49

liked a model about 1 month ago

fishaudio/fish-agent-v0.1-3b

Audio-to-Audio • Updated Nov 1, 2024 • 724 • 238

reacted to MonsterMMORPG's post with 🔥 3 months ago

Post

4116

Huge news for Kohya GUI - Now you can fully Fine Tune / DreamBooth FLUX Dev with as low as 6 GB GPUs without any quality loss compared to 48 GB GPUs - Moreover, Fine Tuning yields better results than any LoRA training could

Config Files
I published all configs here : https://www.patreon.com/posts/112099700

Tutorials
Fine tuning tutorial in production

Windows FLUX LoRA training (fine tuning is same just config changes) : https://youtu.be/nySGu12Y05k

Cloud FLUX LoRA training (RunPod and Massed Compute ultra cheap) : https://youtu.be/-uhL2nW7Ddw

LoRA Extraction
The checkpoint sizes are 23.8 GB but you can extract LoRA with almost no loss quality - I made a research and public article / guide for this as well

LoRA extraction guide from Fine Tuned checkpoint is here : https://www.patreon.com/posts/112335162

Info
This is just mind blowing. The recent improvements Kohya made for block swapping is just amazing.

Speeds are also amazing that you can see in image 2 - of course those values are based on my researched config and tested on RTX A6000 - same speed as almost RTX 3090

Also all trainings experiments are made at 1024x1024px. If you use lower resolution it will be lesser VRAM + faster speed

The VRAM usages would change according to your own configuration - likely speed as well

Moreover, Fine Tuning / DreamBooth yields better results than any LoRA could

Installers
1-Kohya GUI accurate branch and Windows Torch 2.5 Installers and test prompts shared here : https://www.patreon.com/posts/110879657

The link of Kohya GUI with accurate branch : https://github.com/bmaltais/kohya_ss/tree/sd3-flux.1