Running
14
👁
Alina
iblub
·
AI & ML interests
None yet
Recent Activity
liked
a Space
18 days ago
timm/timmAttentionViz
updated
a model
5 months ago
iblub/idefics2-8b-mwm-finetuned-qlora_8bit_10e
updated
a model
6 months ago
iblub/idefics2-8b-mwm-finetuned-8bit
Organizations
None yet
iblub's activity
liked
a
Space
18 days ago
updated
a
model
5 months ago
updated
3
models
6 months ago
Havent come to finetuning it myself, but UDOP also caught my attention:
https://huggingface.co/microsoft/udop-large
updated
a
collection
12 months ago
upvoted
a
paper
12 months ago
reacted to
clem's
post with 🤗
about 1 year ago
Post
Is synthetic data the future of AI? 🔥🔥🔥
@HugoLaurencon @Leyo & @VictorSanh are introducing HuggingFaceM4/WebSight , a multimodal dataset featuring 823,000 pairs of synthetically generated HTML/CSS codes along with screenshots of the corresponding rendered websites to train GPT4-V-like models 🌐💻
While crafting their upcoming foundation vision language model, they faced the challenge of converting website screenshots into usable HTML/CSS codes. Most VLMs suck at this and there was no public dataset available for this specific task, so they decided to create their own.
They prompted existing LLMs to generate 823k HTML/CSS codes of very simple websites. Through supervised fine-tuning of a vision language model on WebSight, they were able to generate the code to reproduce a website component, given a screenshot.
You can explore the dataset here: HuggingFaceM4/WebSight
What do you think?
@HugoLaurencon @Leyo & @VictorSanh are introducing HuggingFaceM4/WebSight , a multimodal dataset featuring 823,000 pairs of synthetically generated HTML/CSS codes along with screenshots of the corresponding rendered websites to train GPT4-V-like models 🌐💻
While crafting their upcoming foundation vision language model, they faced the challenge of converting website screenshots into usable HTML/CSS codes. Most VLMs suck at this and there was no public dataset available for this specific task, so they decided to create their own.
They prompted existing LLMs to generate 823k HTML/CSS codes of very simple websites. Through supervised fine-tuning of a vision language model on WebSight, they were able to generate the code to reproduce a website component, given a screenshot.
You can explore the dataset here: HuggingFaceM4/WebSight
What do you think?
- 12 replies
updated
2
collections
about 1 year ago
updated
a
model
over 1 year ago
Add link to Panda Gym paper
#1 opened over 1 year ago
by
qgallouedec
updated
a
model
almost 2 years ago