Ross Wightman

rwightman

AI & ML interests

Computer vision, transfer learning, semi/self supervised learning, robotics.

Recent Activity

Organizations

Hugging Face's profile picture PyTorch Image Models's profile picture Spaces-explorers's profile picture Flax Community's profile picture LAION eV's profile picture kotol's profile picture Pixel Parsing's profile picture

rwightman's activity

New activity in timm/coat_tiny.in1k about 6 hours ago
New activity in timm/coat_lite_small.in1k about 6 hours ago
New activity in timm/coat_mini.in1k about 6 hours ago
New activity in timm/coat_lite_medium.in1k about 6 hours ago
New activity in timm/levit_256.fb_dist_in1k about 6 hours ago
New activity in timm/coat_lite_mini.in1k about 6 hours ago
New activity in timm/coat_small.in1k about 6 hours ago
New activity in laion/relaion2B-multi-research 13 days ago

Request: DOI

2
#1 opened 13 days ago by
elliottd
New activity in pixparse/pdfa-eng-wds 13 days ago
New activity in timm/ViT-SO400M-14-SigLIP2-378 20 days ago

Model size seems odd

3
#1 opened 20 days ago by
bbb42
reacted to csabakecskemeti's post with ๐Ÿค—๐Ÿš€ 22 days ago
view post
Post
2762
Testing Training on AMD/ROCm the first time!

I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)

For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.

Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
ยท