Mathias Nielsen's picture

Mathias Nielsen

mathiasn1

·

https://grandaiwizard.com/

AI & ML interests

🏢 Senior Machine Learning Engineer @ https://mediacatch.io/

Recent Activity

updated a collection about 19 hours ago

updated a collection about 19 hours ago

updated a collection about 19 hours ago

View all activity

Organizations

mathiasn1's activity

upvoted an article 5 days ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

• 158

upvoted an article 12 days ago

Article

FastRTC: The Real-Time Communication Library for Python

14 days ago

• 134

upvoted a collection 17 days ago

GemmaX2

GemmaX2 language models, including pretrained and instruction-tuned models of 2 sizes, including 2B, 9B. • 7 items • Updated Feb 7 • 20

upvoted 2 collections 23 days ago

Finnish Whisper speech recognition

Whisper models finetuned for Finnish in various formats • 7 items • Updated Dec 31, 2024 • 1

Ahma models

12 items • Updated Feb 3 • 3

upvoted a collection 25 days ago

NV-Embed

NV-Embed is a generalist embedding model encompassing retrieval, reranking, classification, clustering, STS tasks. • 3 items • Updated Jan 17 • 12

upvoted 2 articles about 1 month ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.15k

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 800

upvoted 2 articles about 2 months ago

Article

We now support VLMs in smolagents!

Jan 24

• 92

Article

Mastering Long Contexts in LLMs with KVPress

By

and 1 other •

Jan 23

• 64

upvoted 2 collections about 2 months ago

Nordic embedding training data

This is a collection of synthetic datasets for embedding model training in Danish, Swedish and Norwegian (bokmål). • 15 items • Updated Jan 26 • 4

NB-Whisper

Models based on Whisper from OpenAI, and trained on data from Språkbanken and the digital collection at the National Library of Norway. • 7 items • Updated Nov 30, 2024 • 12

upvoted an article 2 months ago

Article

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

By

•

Jan 3

• 36

upvoted a collection 2 months ago

DeepSeek-V3

3 items • Updated Jan 6 • 195

upvoted 3 collections 3 months ago

NB-Llama 3.x

NOTE: CURRENTLY THERE ARE CONVERTION-ERRORS IN THIS MODELS. TEMPORARY PUT OFFLINE. LLama 3.x models in various sizes. • 9 items • Updated Feb 6 • 2

Falcon3

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters. • 40 items • Updated 26 days ago • 83

Danish Text Datasets

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

upvoted a paper 3 months ago

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 111

upvoted 2 collections 3 months ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated 13 days ago • 554

Llama 3.3

This collection hosts the transformers and original repos of the Llama 3.3 • 1 item • Updated Dec 6, 2024 • 142