Jonna Matthiesen

JonnaMat's activity

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

updated a model 1 day ago

embedl/Cosmos-Reason2-2B-W4A16-Edge2

Image-Text-to-Text • 2B • Updated 1 day ago • 14.6k • 11

updated a Space 1 day ago

Running

4

Edge Inference Benchmarks

🚀

4

On-Device benchmarks across devices and models.

New activity in embedl/Edge-Inference-Benchmarks 1 day ago

Demo

#5 opened 4 days ago by

JonnaMat

updated a dataset 1 day ago

embedl/documentation-images

Viewer • Updated 1 day ago • 7 • 4.04k

updated 3 collections 2 days ago

Cosmos-Reason2

Collection

nvidia/Cosmos-Reason2 multi-modal reasoning models optimized by Embedl. • 8 items • Updated 2 days ago • 4

EdgeN

Collection

Quantization strategy where most weights are converted to INT4, activations remain in FP16, and sensitive layers are preserved in FP16. • 5 items • Updated 2 days ago • 1

FlashHead

Collection

Efficient Drop-In Replacement for the Classification Head in Language Model Inference. • 19 items • Updated 2 days ago • 1

reacted to AINovice2005's post with 👍 3 days ago

view post

Post

362

Pro tip: If you are finetuning any model with tensorboard logs enabled, be sure to upload them to HF Hub as event artifacts, they can be viewed instantly. 🚀

I previously remembered this done in the notus model release: argilla/notus-7b-v1

Examples:

AINovice2005/ModernBERT-base-lora-cicflow-1m-r8

AINovice2005/ModernBERT-base-lora-cicflow-1m-r4

AINovice2005/ModernBERT-base-lora-cicflow-1m-r16

cc: @davidberenstein1957

See translation

👍

2

2

+

Reply

replied to their post 3 days ago

view reply

🤓 Want to learn more about FlashHead? Check out this blog post: https://huggingface.co/blog/JonnaMat/flashhead

published an article 3 days ago

view article

Article

FlashHead: Accelerating Language Model Inference ~ *Efficient drop-in replacement for the classification head*

• 

3 days ago

•

1