Rasmus Aagaard's picture

Rasmus Aagaard

rasgaard

·

https://rasgaard.com

AI & ML interests

Interested in using LLMs in products, evaluation of those products and small models

Recent Activity

upvoted an article 3 days ago

Running Large Transformer Models on Mobile and Edge Devices

upvoted an article 8 days ago

Streaming datasets: 100x More Efficient

published an article 9 days ago

Local on-device LLM with RAG through the browser

View all activity

Organizations

upvoted an article 3 days ago

Article

Running Large Transformer Models on Mobile and Edge Devices

By

•

4 days ago

• 10

upvoted an article 8 days ago

Article

Streaming datasets: 100x More Efficient

12 days ago

• 56

upvoted an article 17 days ago

Article

Sentence Transformers is joining Hugging Face!

17 days ago

• 73

upvoted an article 24 days ago

Article

Get your VLM running in 3 simple steps on Intel CPUs

24 days ago

• 18

upvoted 2 articles about 1 month ago

Article

SOTA OCR with Core ML and dots.ocr

Oct 2

• 58

Article

There is no such thing as a tokenizer-free lunch

By

•

Sep 25

• 86

upvoted a paper about 2 months ago

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Paper • 2402.14905 • Published Feb 22, 2024 • 134

upvoted an article about 2 months ago

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

By

•

Jan 30

• 161

upvoted a paper 2 months ago

TorchAO: PyTorch-Native Training-to-Serving Model Optimization

Paper • 2507.16099 • Published Jul 21 • 6

upvoted an article 5 months ago

Article

AI Policy @🤗: Response to the 2025 National AI R&D Strategic Plan

By

and 2 others •

Jun 2

• 14

upvoted a collection 5 months ago

POTION

These are the flagship POTION models. Load them and use them with model2vec (https://github.com/MinishLab/model2vec) or sentence-transformers • 6 items • Updated May 23 • 13

upvoted 2 articles 6 months ago

Article

Blazingly fast whisper transcriptions with Inference Endpoints

May 13

• 79

Article

Vision Language Models (Better, faster, stronger)

May 12

• 561

upvoted a collection 7 months ago

Orpheus Multilingual Research Release

Beta Release of multilingual models. • 12 items • Updated Apr 10 • 104

upvoted an article 9 months ago

Article

From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages

By

and 1 other •

Feb 11

• 33

upvoted 2 collections 11 months ago

Danish Text Datasets

These include high-quality Danish text datasets for pre-training, fine-tuning, etc. • 16 items • Updated Dec 15, 2024 • 3

FineWeb2 Collaborative Annotation Sprint

6 items • Updated Jul 8 • 9

upvoted a paper over 1 year ago

On convex decision regions in deep network representations

Paper • 2305.17154 • Published May 26, 2023 • 1

upvoted an article over 1 year ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

• 178