Peter Szemraj's picture

Peter Szemraj PRO

pszemraj

·

https://pszemraj.carrd.co/

pszemraj

AI & ML interests

metallic intuition

Recent Activity

liked a model 2 days ago

sshh12/badseek-v2

new activity 4 days ago

pszemraj/Ballpark-Trivia-XL:Adding `safetensors` variant of this model

upvoted a paper 5 days ago

Demystifying Long Chain-of-Thought Reasoning in LLMs

View all activity

Organizations

pszemraj's activity

upvoted 2 papers 5 days ago

Demystifying Long Chain-of-Thought Reasoning in LLMs

Paper • 2502.03373 • Published 11 days ago • 51

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published 10 days ago • 28

upvoted 2 collections 23 days ago

NeMo Curator - Classifier Models

Classifier models that can be used in NeMo Curator for labelling/filtering datasets. • 11 items • Updated 1 day ago • 15

SmolVLM 256M & 500M

Collection for models & demos for even smoller SmolVLM release • 12 items • Updated 24 days ago • 68

upvoted an article 23 days ago

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

25 days ago

• 133

upvoted a collection about 1 month ago

Deita

14 items • Updated May 20, 2024 • 12

upvoted 3 papers about 1 month ago

An Empirical Study of Autoregressive Pre-training from Videos

Paper • 2501.05453 • Published Jan 9 • 37

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published Jan 14 • 55

Tensor Product Attention Is All You Need

Paper • 2501.06425 • Published Jan 11 • 83

upvoted a collection about 1 month ago

DolphinLabeled Datasets

Eric Hartford has added labels to help you filter datasets, for your pleasure. • 5 items • Updated Jan 6 • 12

upvoted a paper about 1 month ago

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization

Paper • 2412.18525 • Published Dec 24, 2024 • 75

upvoted a collection about 2 months ago

Embedding Model Datasets

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 68 items • Updated 2 days ago • 104

upvoted 4 papers about 2 months ago

How to Synthesize Text Data without Model Collapse?

Paper • 2412.14689 • Published Dec 19, 2024 • 50

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Paper • 2412.15204 • Published Dec 19, 2024 • 33

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 345

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published Dec 18, 2024 • 132

upvoted a collection about 2 months ago

ModernBERT

Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated Dec 19, 2024 • 134

upvoted 3 papers about 2 months ago

Byte Latent Transformer: Patches Scale Better Than Tokens

Paper • 2412.09871 • Published Dec 13, 2024 • 92

OmniPred: Language Models as Universal Regressors

Paper • 2402.14547 • Published Feb 22, 2024 • 12

From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples

Paper • 2404.07544 • Published Apr 11, 2024 • 20