David Golchinfar PRO

DavidGF

VAGOsolutions

·

https://vago-solutions.ai

AI & ML interests

finetune llms, improve german language understanding and generated text of llms

Recent Activity

upvoted an article 1 day ago

Token Pooling-Aware Training for Multi-Vector Embedding Models

liked a Space 1 day ago

VAGOsolutions/german-legal-embedding-leaderboard

liked a dataset 1 day ago

VAGOsolutions/openlegalretrieval-de

View all activity

Organizations

upvoted an article 1 day ago

Article

Token Pooling-Aware Training for Multi-Vector Embedding Models

tomaarsen

•

1 day ago

• 28

upvoted a collection 1 day ago

SauerkrautLM-MoEdernColBERT-Legal

German legal ColBERT retrievers on the MoEdernBERT architecture (1.5M, 27M, 115M) with benchmark, leaderboard and demo • 6 items • Updated 1 day ago • 2

upvoted a collection 8 days ago

SauerkrautLM-GLiNEREL

Text in, knowledge graph out. Joint NER, PII detection and relation extraction in one encoder pass. • 4 items • Updated 8 days ago • 16

upvoted a collection 20 days ago

SauerkrautLM-MoEdernColBERT

Multilingual ColBERT retrievers on the MoEdernBERT architecture (1.5M, 27M, 115M) with GGUF and CoreML builds • 9 items • Updated 20 days ago • 13

upvoted a collection 2 months ago

MultiVectorEncoder integrations

88 items • Updated Oct 8 • 4

upvoted an article 3 months ago

Article

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

+1

tomaarsen, NohTow, raphaelsty

•

Aug 18

• 120

upvoted an article 5 months ago

Article

Party is over: regularizing ColBERT models to fix efficient ANN methods

lightonai

•

Jun 16

• 26

upvoted an article 9 months ago

Article

Kimi K2.5: Still Worth It After Two Weeks?

mlabonne

•

Feb 23

• 10

upvoted a collection 9 months ago

Qwen3.5

21 items • Updated Mar 9 • 1.83k

upvoted 2 articles 10 months ago

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

lightonai

•

Jan 19

• 106

Article

🚀 Release: parakeet-primeline – High-Efficiency German ASR

flozi00

•

Jan 13

• 4

upvoted a collection 11 months ago

SauerkrautLM-Vision-Document-Retrieval

7 items • Updated Dec 15, 2025 • 9

upvoted 5 articles about 1 year ago

Article

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

lightonai

•

Oct 23, 2025

• 75

Article

Sentence Transformers is joining Hugging Face!

tomaarsen

•

Oct 22, 2025

• 89

Article

ModernVBERT: Towards Smaller Visual Document Retrievers

paultltc

•

Oct 3, 2025

• 47

Article

mmBERT: ModernBERT goes Multilingual

+4

mmarone, orionweller, will-fleshman, eugene-yang, dlawrie, vandurme

•

Sep 9, 2025

• 157

Article

Exploring Environments Hub: Your Language Model needs better (open) environments to learn

anakin87

•

Sep 4, 2025

• 32

upvoted a collection about 1 year ago

Marvis-TTS-250m-v0.1

5 items • Updated Aug 26, 2025 • 26

upvoted an article about 1 year ago

Article

Building Enterprise-Ready Text Classifiers in Minutes with Adaptive Learning

codelion

•

Aug 9, 2025

• 12

upvoted a collection over 1 year ago

SauerkrautLM-Multilingual-(Reason)-ColBERT

SauerkrautLM ColBERT is a suite of Late-Interaction retrieval models built with PyLate’s ColBERT architecture and tuned for seven European languages. • 7 items • Updated Aug 3, 2025 • 21