Peter Szemraj PRO

pszemraj's activity

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

liked a dataset 6 days ago

FutureMa/DramaBench

Viewer • Updated 5 days ago • 600 • 471 • 109

New activity in pszemraj/long-t5-tglobal-xl-16384-booksci-summary-plos-10k 7 days ago

Adding `safetensors` variant of this model

#1 opened 7 days ago by

SFconvertbot

New activity in pszemraj/flan-t5-xl-instructiongen 7 days ago

Adding `safetensors` variant of this model

#2 opened 7 days ago by

SFconvertbot

New activity in pszemraj/long-t5-tglobal-xl-16384-booksci-summary-v1 7 days ago

Adding `safetensors` variant of this model

#2 opened 7 days ago by

SFconvertbot

New activity in pszemraj/neuspell-scrnn-probwordnoise 7 days ago

Adding `safetensors` variant of this model

#1 opened 7 days ago by

SFconvertbot

upvoted 2 papers 10 days ago

From Word to World: Can Large Language Models be Implicit Text-based World Models?

Paper • 2512.18832 • Published 15 days ago • 11

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Paper • 2512.20757 • Published 13 days ago • 16

upvoted a paper 11 days ago

NVIDIA Nemotron 3: Efficient and Open Intelligence

Paper • 2512.20856 • Published 13 days ago • 29

upvoted a paper 12 days ago

Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation

Paper • 2512.20352 • Published 13 days ago • 2

New activity in nvidia/NitroGen 12 days ago

Performance bad in game client

6

#6 opened 13 days ago by

wkruan

upvoted a paper 13 days ago

Are We on the Right Way to Assessing LLM-as-a-Judge?

Paper • 2512.16041 • Published 19 days ago • 32

upvoted a paper 14 days ago

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Paper • 2512.17909 • Published 17 days ago • 36

liked a model 16 days ago

inclusionAI/LLaDA2.0-mini

Text Generation • 16B • Updated 17 days ago • 9.13k • 51

upvoted a collection 16 days ago

LLaDA 2.0

Collection

7 items • Updated 12 days ago • 39

upvoted a paper 17 days ago

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Paper • 2512.16649 • Published 18 days ago • 24

upvoted a collection 17 days ago

T5Gemma 2

Collection

3 items • Updated 18 days ago • 57

liked a Space 18 days ago

Running on Zero

Featured

705

TRELLIS.2

🏢

705

High-fidelity 3D Generation from images

liked a model 18 days ago

microsoft/TRELLIS.2-4B

Image-to-3D • Updated 9 days ago • 520

upvoted a paper 18 days ago

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Paper • 2512.14052 • Published 20 days ago • 40

New activity in allenai/Olmo-3.1-32B-Instruct 18 days ago

use_cache set to false?

👀 1

#4 opened 18 days ago by

pszemraj