Simon Brandeis

sbrandeis's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a dataset 2 days ago

huggingface/documentation-images

Updated 1 day ago • 2.57M • 40

liked a model about 1 month ago

multimodalart/eery-liminal-space

Text-to-Image • Updated Sep 12 • 361 • • 9

liked a model about 2 months ago

ostris/OpenFLUX.1

Text-to-Image • Updated Oct 3 • 15.3k • 585

liked a Space 3 months ago

Running on L40S

659

🎥

CogVideoX-5B

Text-to-Video

New activity in huggingface/documentation-images 3 months ago

Add screenshots for the new billing docs

#357 opened 3 months ago by sbrandeis

updated 2 Spaces 3 months ago

Sleeping

💬

Checkaaa2

No application file

📚

Checkaaa

New activity in dev-mode-explorers/README 4 months ago

How to actually debug gradio code?

3

#14 opened 5 months ago by darknoon

New activity in meta-llama/Llama-3.1-8B-Instruct 4 months ago

Add `base_model` metadata

#72 opened 4 months ago by sbrandeis

liked a model 5 months ago

dataautogpt3/OpenDalleV1.1

Text-to-Image • Updated Jan 19 • 27.2k • • 495

New activity in dev-mode-explorers/README 5 months ago

git status stuck: fetching git changes

3

#12 opened 5 months ago by keval-sha

[FEEDBACK] Spaces Dev Mode

53

#3 opened 6 months ago by sbrandeis

LL-MWA-4o

1

#8 opened 6 months ago by SitonmyFACEBOOK

Upload app.py

1

#11 opened 5 months ago by waqashayder

upvoted an article 5 months ago

view article

Article

BrAIn: next generation neurons?

By •

Jun 5

• 15

Reacted to louisbrulenaudet's post with ❤️ 5 months ago

view post

Post

3195

Reply

I am delighted to announce the publication of my LegalKit, a French labeled dataset built for legal ML training 🤗

This dataset comprises multiple query-document pairs (+50k) curated for training sentence embedding models within the domain of French law.

The labeling process follows a systematic approach to ensure consistency and relevance:
- Initial Query Generation: Three instances of the LLaMA-3-70B model independently generate three different queries based on the same document.
- Selection of Optimal Query: A fourth instance of the LLaMA-3-70B model, using a dedicated selection prompt, evaluates the generated queries and selects the most suitable one.
- Final Label Assignment: The chosen query is used to label the document, aiming to ensure that the label accurately reflects the content and context of the original text.

Dataset: louisbrulenaudet/legalkit

Stay tuned for further updates and release information 🔥

@clem , if we can create an "HF for Legal" organization, similar to what exists for journalists, I am available!

Note : My special thanks to @alvdansen for their illustration models ❤️

• 

• 
• 
• 2 replies

·

👍

8

8

❤️

7

7

🚀

3

3

👀

1

1

🧠

1

1

+

Reacted to Xenova's post with 🔥 5 months ago

view post

Post

5959

Reply

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯

It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW!
- Demo: Xenova/florence2-webgpu
- Models: https://huggingface.co/models?library=transformers.js&other=florence2
- Source code: https://github.com/xenova/transformers.js/tree/v3/examples/florence2-webgpu

🔥

20

20

🚀

6

6

👀

4

4

❤️

3

3

🧠

1

1

🤝

1

1

+

updated 2 Spaces 5 months ago

Running

1

📉

Example: Javascript

Running

1

🔥

Example: Python