Stefan Schweter's picture

In a Training Loop 🔄

Stefan Schweter PRO

stefan-it

·

https://schweter.bayern

AI & ML interests

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

Recent Activity

upvoted a collection about 15 hours ago

NVIDIA Nemotron v3

liked a dataset about 15 hours ago

Viet-Mistral/CulturaY

upvoted a collection 1 day ago

MixtureVitae study models and datasets

View all activity

Organizations

upvoted a collection about 15 hours ago

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 12 items • Updated about 15 hours ago • 176

upvoted a collection 1 day ago

MixtureVitae study models and datasets

Collection of models and dataset related to MixtureVitae, open and fully reproducible pretraining dataset built from permissive sources • 16 items • Updated 27 days ago • 1

upvoted an article 6 days ago

Article

Scaling Pedagogical Pre-training: From Optimal Mixing to 10 Billion Tokens

6 days ago

•

3

upvoted a collection 10 days ago

🤏 Smol-Data

Tried and tested mixes for strong pretraining. Inspired by https://huggingface.co/blog/codelion/optimal-dataset-mixing • 14 items • Updated 10 days ago • 12

upvoted a paper 10 days ago

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

Paper • 2602.22207 • Published 15 days ago • 41

upvoted a paper 15 days ago

NanoKnow: How to Know What Your Language Model Knows

Paper • 2602.20122 • Published 17 days ago • 7

upvoted an article 15 days ago

Article

Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?

16 days ago

•

17

upvoted a paper 16 days ago

The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder

Paper • 2602.18487 • Published 29 days ago • 5

upvoted a collection 22 days ago

Avey B1 experimental

Experimental pre-trained checkpoints for Avey-B1 • 3 items • Updated 17 days ago • 3

upvoted 2 papers 22 days ago

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Paper • 2602.15547 • Published 23 days ago • 26

Avey-B

Paper • 2602.15814 • Published 23 days ago • 3

upvoted a collection 22 days ago

Aya Datasets

The Aya Collection is a massive multilingual collection for over 100 languages consisting of 513 million instances of prompts and completions. • 5 items • Updated Jul 31, 2025 • 27

upvoted 3 papers 28 days ago

LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules

Paper • 2602.10993 • Published 29 days ago • 1

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning

Paper • 2602.11149 • Published 29 days ago • 15

SteuerLLM: Local specialized large language model for German tax law analysis

Paper • 2602.11081 • Published 29 days ago • 1

upvoted a collection 29 days ago

GLM-5

2 items • Updated 29 days ago • 31

upvoted a paper about 1 month ago

Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay

Paper • 2602.06942 • Published Feb 6 • 3

upvoted a collection about 1 month ago

GLiNER- Linker

GLiNER-bi-Encoder models for entity linking with the GLiNKER framework • 3 items • Updated Feb 3 • 6

upvoted a paper about 1 month ago

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Paper • 2601.22146 • Published Jan 29 • 9

upvoted a collection about 2 months ago

GutenOCR

3 items • Updated Jan 22 • 6