Moritz Laurer's picture

Moritz Laurer

MoritzLaurer

·

https://www.linkedin.com/in/moritz-laurer/

AI & ML interests

None yet

Recent Activity

posted an update about 5 hours ago

🚀 Releasing a new zeroshot-classifier based on ModernBERT! Some key takeaways: - ⚡ Speed & efficiency: It's multiple times faster and uses significantly less memory than DeBERTav3. You can use larger batch sizes and enabling bf16 (instead of fp16) gave me a ~2x speed boost as well - 📉 Performance tradeoff: It performs slightly worse than DeBERTav3 on average across my zeroshot classification task collection - 🧠 Use cases: I recommend using it for scenarios requiring speed and a larger context window (8k). - 💡 What’s next? I’m preparing a newer version trained on better + longer synthetic data to fully leverage the 8k context window and improve upon the training mix of my older zeroshot-v2.0 models. I also hope that there will be a multilingual variant in the future. Great work by https://huggingface.co/answerdotai ! If you’re looking for a high-speed zeroshot classifier, give it a try! 📄 Resources below: 👇 Base model: https://huggingface.co/MoritzLaurer/ModernBERT-base-zeroshot-v2.0 Large model: https://huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0 Updated zeroshot collection: https://huggingface.co/collections/MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f ModernBERT collection with paper: https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb

liked a Space about 6 hours ago

reach-vb/2024-ai-timeline

updated a collection about 6 hours ago

Zeroshot Classifiers

View all activity

Articles

Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap

Synthetic data: save money, time and carbon with open source

Organizations

MoritzLaurer's activity

upvoted an article 13 days ago

Article

🌁#81: Key AI Concepts to Follow in 2025

By

•

14 days ago

• 19

upvoted a paper 17 days ago

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published 19 days ago • 118

upvoted a collection 21 days ago

Qwen2-VL

Vision-language model series based on Qwen2 • 16 items • Updated Dec 6, 2024 • 186

upvoted a collection about 1 month ago

PaliGemma 2 Release

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 23 items • Updated 24 days ago • 123

upvoted a paper about 1 month ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 121

upvoted a collection about 1 month ago

PixMo

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated about 1 hour ago • 53

upvoted a collection about 2 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. • 45 items • Updated Nov 28, 2024 • 453

upvoted a collection 2 months ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated 15 days ago • 197

upvoted a paper 2 months ago

GPT-4o System Card

Paper • 2410.21276 • Published Oct 25, 2024 • 83

upvoted a collection 2 months ago

Dinov2

5 items • Updated Jan 16, 2024 • 15

upvoted 3 articles 3 months ago

Article

How to optimize your data labelling project with custom interfaces

By

•

Oct 16, 2024

• 18

Article

Inference Endpoints Changelog 🚀

By

•

Oct 11, 2024

• 19

Article

Welcome, Gradio 5

Oct 9, 2024

• 97

upvoted 2 papers 3 months ago

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published Sep 27, 2024 • 94

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published Sep 25, 2024 • 106

upvoted a collection 3 months ago

Molmo

Artifacts for open multimodal language models. • 5 items • Updated about 1 hour ago • 291

upvoted an article 4 months ago

Article

2024 Security Feature Highlights

Aug 6, 2024

• 16

upvoted a collection 4 months ago

Moshi v0.1 Release

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18, 2024 • 225

upvoted an article 4 months ago

Article

Accelerate 1.0.0

Sep 13, 2024

• 52

upvoted a paper 4 months ago

Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text

Paper • 2409.02078 • Published Sep 3, 2024 • 10