🔄 In a Training Loop

Attention Signs

attn-signs

·

https://raumberg.github.io/attn-signs-center/

Raumberg

AI & ML interests

Deep Learning, Large Language Models, Reinforcement Learning, Quantum Computing, Mathematics.

Organizations

None yet

upvoted 2 collections about 1 year ago

Russian Preference Datasets

3 items • Updated Aug 28, 2025 • 2

Math Instruct datasets in Russian

Collected Olympiad and final exam tasks, automatically generated tasks, as well as automatically translated datasets. Work in progress... • 5 items • Updated Feb 10 • 1

upvoted a paper over 1 year ago

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Paper • 2506.13585 • Published Jun 16, 2025 • 279

upvoted 4 collections over 1 year ago

Gromov series [GRPO]

Specific datasets particulary effective in GRPO • 8 items • Updated Aug 4, 2025 • 1

Datasets [RU]

SFT / RL high-quality datasets • 12 items • Updated Aug 13, 2025 • 2

Reasoning Models [RU]

Collection of reasoning models • 8 items • Updated Sep 1, 2025 • 1

SFT / Instruct Models [RU]

Finetuned Instruct Models • 6 items • Updated Aug 4, 2025 • 1