Vadim Borisov PRO

vdmbrsv's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 15 hours ago

tabularisai/Faust-1

Text Generation • 2B • Updated about 12 hours ago • 152 • 6

liked a Space about 16 hours ago

Running

16

Leaderboard

🥇

16

liked a Space 1 day ago

Running

Featured

25

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

25

Who needs 1T parameters? Olympiad proofs with a 4B model

upvoted a paper 7 days ago

MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration

Paper • 2602.01734 • Published 15 days ago • 32

updated a model 11 days ago

tabularisai/multilingual-sentiment-analysis

Text Classification • 0.1B • Updated 11 days ago • 205k • • 358

authored a paper 14 days ago

Do Chatbot LLMs Talk Too Much? The YapBench Benchmark

Paper • 2601.00624 • Published Jan 2 • 1

upvoted a paper 14 days ago

Do Chatbot LLMs Talk Too Much? The YapBench Benchmark

Paper • 2601.00624 • Published Jan 2 • 1

liked a dataset 22 days ago

LEXam-Benchmark/LEXam

Viewer • Updated 21 days ago • 7.54k • 685 • 39

New activity in Qwen/Qwen3-1.7B 23 days ago

Update README.md

#18 opened 23 days ago by

vdmbrsv

updated a model 24 days ago

tabularisai/eu-pii-safeguard

Token Classification • 0.6B • Updated 24 days ago • 952 • 18

updated a collection 26 days ago

Faust-1-Foundation Model for German Language

Collection

1 item • Updated 26 days ago • 1

liked a model 26 days ago

tabularisai/Faust-1

Text Generation • 2B • Updated about 12 hours ago • 152 • 6

published a model 26 days ago

tabularisai/Faust-1

Text Generation • 2B • Updated about 12 hours ago • 152 • 6

upvoted a collection about 1 month ago

🇩🇪German SFT and DPO datasets

Collection

Datasets that can be used for LLM training with axolotl, trl or llama_factory. • 33 items • Updated Jan 23, 2025 • 13

liked a dataset about 1 month ago

PleIAs/SYNTH

Viewer • Updated Nov 11, 2025 • 68M • 37.4k • 247

updated a Space about 1 month ago

Running

7

YapBench

🤐

7

Measuring how wordy LLMs are when a short answer would do

upvoted 2 articles about 2 months ago

view article

Article

Deriving the DPO Loss from First Principles

• 

Dec 30, 2025

•

6

view article

Article

SYNTH: the new data frontier

• 

Nov 10, 2025

•

9

liked a dataset about 2 months ago

tabularisai/yapbench_dataset

Viewer • Updated Dec 25, 2025 • 304 • 22 • 2

updated a dataset about 2 months ago

tabularisai/yapbench_dataset

Viewer • Updated Dec 25, 2025 • 304 • 22 • 2