vik's picture

vik PRO

vikhyatk

·

AI & ML interests

None yet

Organizations

Posts 11

Post

2895

Disappointed that Golden Gate Claude couldn't process images? Want to learn how to use activation vectors to steer VLMs?

Try out the vikhyatk/contemplative-moondream space, and check out the notebook I released showing how to obtain control vectors! ⬇️

https://github.com/vikhyat/moondream/blob/main/notebooks/RepEng.ipynb

Post

2998

Just released a new version of vikhyatk/moondream2 - now supporting higher resolution images (up to 756x756)!

TextVQA score (which measures the model's ability to read and reason about text in images) is up from 53.1 to 57.2 (+7.7%). Other visual question answering and counting benchmark results are up ~0.5%.

spaces 3

Running on Zero

moondream2

a tiny vision language model

Running on Zero

moondream1

Running on Zero

Contemplative moondream

let's talk about the meaning of life

models 4

vikhyatk/moondream2

Image-Text-to-Text • Updated 1 day ago • 66.7k • 517

vikhyatk/moondream-next

Text Generation • Updated Jun 10 • 2 • 7

vikhyatk/moondream1

Text Generation • Updated Feb 7 • 123k • 474

vikhyatk/moondream0

Updated Dec 30, 2023 • 11

datasets 10

vikhyatk/openimages-human-labels

Viewer • Updated about 19 hours ago • 110k • 1

vikhyatk/docmatix-single

Viewer • Updated 3 days ago • 565k • 17 • 3

vikhyatk/st-vqa

Viewer • Updated 12 days ago • 18.9k

vikhyatk/openimages-bbox

Viewer • Updated 12 days ago • 1.89M • 61 • 6

vikhyatk/gqa

Viewer • Updated 20 days ago • 82.4k • 21

vikhyatk/lnqa

Viewer • Updated Apr 25 • 303k • 39 • 70

vikhyatk/coco-val

Viewer • Updated Apr 24 • 5k • 103

vikhyatk/cc-12m

Viewer • Updated Feb 3 • 12.4M • 2

vikhyatk/cc-3m

Updated Feb 2 • 2

vikhyatk/synthetic-pepe

Viewer • Updated Oct 25, 2023 • 504 • 3 • 8