🔄 In a Training Loop

Stefan Schweter PRO

stefan-it

·

http://schweter.bayern

AI & ML interests

Flair + Flukes Library 💕, NER & PoS Tagging, LM Pretraining (mostly encoder-only & encoder-decoder), Historical Language Models, German Language Models, Bavarian NLP 🥨, xLSTM

Recent Activity

liked a dataset about 23 hours ago

sg-sy/ChronosAlign

liked a Space 6 days ago

huggingface/moe-blogpost

liked a dataset 6 days ago

lilt-ai/tau-bench-lilt

View all activity

Organizations

upvoted an article 11 days ago

Article

Sliding window beats linear attention, but only on short answers

sirluk

•

11 days ago

• 6

upvoted an article 14 days ago

Article

Welcome Le Chonk: Mistral Large 4 on Hugging Face

+9

merve, alvarobartt, ror, cyrilvallez, qgallouedec, ehcalabres, juanjucm, ngxson, pcuenq, burtenshaw, ariG23498

•

15 days ago

• 94

upvoted a paper 22 days ago

PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States

Paper • 2610.29545 • Published 23 days ago • 18

upvoted an article 23 days ago

Article

NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models

nvidia

•

23 days ago

• 68

upvoted a paper 24 days ago

Kronecker Delta Rule for Long Context Linear Attention

Paper • 2610.26834 • Published 25 days ago • 32

upvoted a collection 24 days ago

KronLSTM

The language models of the paper "Kronecker Delta Rule for Long Context Linear Attention" pretrained on 100B tokens. • 4 items • Updated 24 days ago • 6

upvoted an article 27 days ago

Article

Welcome Beam: a 501B open model you can own, customize, and scale

+1

burtenshaw, merve, pcuenq

•

28 days ago

• 83

upvoted an article 29 days ago

Article

UltraBERT: One Encoder for Classification and Retrieval

dmis-lab

•

30 days ago

• 68

upvoted 2 articles about 1 month ago

Article

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

nvidia

•

Oct 7

• 25

Article

Can LLMs Correct Historical OCR Without Rewriting History?

emanuelaboros

•

Oct 6

• 2

upvoted a paper about 1 month ago

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Paper • 2609.07379 • Published Sep 10 • 2

upvoted a changelog about 1 month ago

Hugging Face Changelog

P(doom) on user profiles

Oct 5

• 365

upvoted an article about 1 month ago

Article

Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs

allenai

•

Oct 1

• 26

upvoted 2 collections about 2 months ago

Flair 2.0 - Named Entity Recognition Models

New state-of-the-art NER models for Flair! Commercial use possible. • 6 items • Updated Oct 2 • 1

Flair 1.0 - All Classic Models

All classic NLP models that ship with Flair. Noncommercial use only. • 23 items • Updated Sep 24 • 1

upvoted an article about 2 months ago

Article

tokenizers v1: encode, decode and scaling, measured

+2

ArthurZ, sbrandeis, mcpotato, lysandre

•

Sep 21

• 97

upvoted a paper about 2 months ago

Augmented Lagrangian Predictive Coding

Paper • 2605.31022 • Published May 29 • 2

upvoted 2 collections 2 months ago

OCR on the Hub

Curated OCR models for documents, languages, handwriting and text in images. Browse five collections with short practical notes. • 5 items • Updated Sep 16 • 13

NeoMME

Meet NeoMME: a family of 260M and 800M Multimodal-Native Multilingual Encoders • 12 items • Updated Sep 28 • 33

upvoted a paper 2 months ago

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

Paper • 2609.03181 • Published Sep 2 • 13