19 107 132

Aurélien-Morgan CLAUDON

Aurelien-Morgan

https://huggingface.co/retrain-pipelines

AI & ML interests

None yet

Recent Activity

new activity about 15 hours ago

blog-explorers/README:Preview dark/light toggle

liked a Space 1 day ago

blog-explorers/README

commented on a paper 2 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

View all activity

Organizations

Aurelien-Morgan's activity

New activity in blog-explorers/README about 15 hours ago

Preview dark/light toggle

#9 opened 2 months ago by

Aurelien-Morgan

liked a Space 1 day ago

README

🐨

commented a paper 2 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 3 days ago • 68 •

liked a dataset 2 days ago

Hcompany/WebClick

Viewer • Updated 2 days ago • 1.64k • 1.38k • 26

commented a paper 3 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 3 days ago • 68 •

upvoted a paper 3 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 3 days ago • 68

upvoted an article 3 days ago

Article

🐯 Liger GRPO meets TRL

and 5 others •

12 days ago

• 36

liked a Space 8 days ago

859

Flux Style Shaping

🚀

Optical illusions and style transfer with FLUX

upvoted an article 11 days ago

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

and 3 others •

14 days ago

• 122

upvoted 2 papers 17 days ago

Aya Vision: Advancing the Frontier of Multilingual Multimodality

Paper • 2505.08751 • Published 23 days ago • 11

Qwen3 Technical Report

Paper • 2505.09388 • Published 23 days ago • 181

reacted to cbensimon's post with 👀 19 days ago

Post

5729

🚀 ZeroGPU medium size is now available as a power-user feature

Nothing too fancy for now—ZeroGPU Spaces still default to large (70GB VRAM)—but this paves the way for:
- 💰 size-based quotas / pricing (medium will offer significantly more usage than large)
- 🦣 the upcoming xlarge size (141GB VRAM)

You can as of now control GPU size via a Space variable. Accepted values:
- auto (future default)
- medium
- large (current default)

The auto mode checks total CUDA tensor size during startup:
- More than 30GB → large
- Otherwise → medium

3 replies

reacted to ordagan's post with ❤️ 19 days ago

Post

2197

Excited to introduce Jamba by AI21
ai21labs/Jamba-v0.1

We are thrilled to announce Jamba, the world’s first production-grade Mamba based model.

Key Features:
- First production-grade Mamba based model built on a novel SSM-Transformer hybrid architecture
- 3X throughput on long contexts compared to Mixtral 8x7B
- Democratizes access to a massive 256K context window
- The only model in its size class that fits up to 140K context on a single GPU

Jamba is based on a novel architecture that combines Mamba and Transformer. While our initial results show great efficiency gains, we expect this to be further explored and improved with the help of the community.

Check out our blog post for more info: https://ai21-labs.webflow.io/blog/announcing-jamba