David Rau

d-rau's activity

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

updated a model 13 days ago

CohereLabs/North-Micro-Vision-Instruct

Image-Text-to-Text • 2B • Updated 13 days ago • 169k • 146

New activity in CohereLabs/North-Micro-Vision-Instruct 16 days ago

delete a trailing comma

#4 opened 16 days ago by

RaushanTurganbay

Update config.json

#3 opened 21 days ago by

RaushanTurganbay

liked a Space 28 days ago

Running on CPU Upgrade

Agents

25

Cohere Parse

🚀

25

Extract text and tables from PDFs and images

New activity in CohereLabs/North-Micro-Vision-Instruct about 1 month ago

Add {% generation %} markers for assistant-only loss masking

🤝 1

#2 opened about 1 month ago by

qgallouedec

Add a response_template for parsing assistant responses

#1 opened about 1 month ago by

qgallouedec

upvoted a collection about 1 month ago

North-Micro-Vision

Collection

MLX quantizations of CohereLabs/North-Micro-Vision-Instruct. • 8 items • Updated Aug 12 • 5

upvoted an article about 1 month ago

view article

Article

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

• 

CohereLabs

•

Aug 12

• 41

liked a model about 1 month ago

CohereLabs/North-Micro-Vision-Instruct

Image-Text-to-Text • 2B • Updated 13 days ago • 169k • 146

published an article about 1 month ago

view article

Article

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

• 

CohereLabs

•

Aug 12

• 41

published a model about 1 month ago

CohereLabs/North-Micro-Vision-Instruct

Image-Text-to-Text • 2B • Updated 13 days ago • 169k • 146

upvoted an article 2 months ago

view article

Article

Introducing North Mini Code: Cohere’s First Model For Developers

• 

CohereLabs

•

Jun 9

• 87

liked a model 4 months ago

CohereLabs/command-a-plus-05-2026-w4a4

Image-Text-to-Text • 219B • Updated Aug 17 • 3.76k • • 246

upvoted a collection 6 months ago

Perception Encoder

Collection

16 items • Updated Mar 2 • 83

upvoted a paper 6 months ago

Tiny Aya: Bridging Scale and Multilingual Depth

Paper • 2603.11510 • Published Mar 12 • 10

New activity in HuggingFaceM4/FineVisionMax 7 months ago

Script to create FineVisionMax

#4 opened 7 months ago by

d-rau

New activity in Misraj/msdd 7 months ago

How to download images

3

#2 opened 7 months ago by

d-rau

New activity in HuggingFaceFW/finepdfs 11 months ago

The "file_path" data field appears to primarily contain cc-index paths rather than WARC paths.

9

#16 opened about 1 year ago by

lnstrument

Were the original PDFs saved?

13

#2 opened about 1 year ago by

staghado

commented a paper about 1 year ago

Set Block Decoding is a Language Model Inference Accelerator

Paper • 2509.04185 • Published Sep 4, 2025 • 54 •

7