Peter Szemraj PRO

pszemraj's activity

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

New activity in mlx-community/Falcon-OCR-bf16 11 days ago

Update weights for Falcon OCR v1.5

#1 opened 11 days ago by

pszemraj

New activity in Edge0/Edge0-35B-A3B-preview 18 days ago

please make an ios app for ease of using your AI model like google's edge gallery app

🚀 2

2

#3 opened 19 days ago by

Narutoouz

commented a paper 21 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 24 days ago • 29 •

5

commented 3 papers about 1 month ago

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published Aug 27 • 40 •

7

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published Aug 27 • 40 •

7

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Paper • 2608.12875 • Published Aug 13 • 16 •

5

New activity in Motif-Technologies/Motif-3-Beta 2 months ago

Why not open source

👀 2

6

#1 opened 2 months ago by

gogo8232

New activity in pszemraj/pdf-ocr 2 months ago

Runtime error?

2

#2 opened 2 months ago by

nbpe97

New activity in EssentialAI/rnj-1.5-instruct 4 months ago

any GGUF ?

1

#1 opened 4 months ago by

dheerapat38

New activity in multimodalart/nano-banana 6 months ago

Space error 500

😔 2

2

#30 opened 6 months ago by

azhan77168

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 6 months ago

The model's self-perception is unstable within a Chinese context.

👀 1

1

#15 opened 6 months ago by

Jianqiao1

commented a paper 6 months ago

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Paper • 2603.24472 • Published Mar 25 • 58 •

7

New activity in nvidia/NVIDIA-Nemotron-Parse-v1.2 7 months ago

transformers code fixes

1

#2 opened 7 months ago by

pszemraj

New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17 8 months ago

Adding `safetensors` variant of this model

#7 opened 8 months ago by

SFconvertbot

New activity in pszemraj/long-t5-tglobal-xl-16384-booksci-summary-plos-10k 9 months ago

Adding `safetensors` variant of this model

#1 opened 9 months ago by

SFconvertbot

New activity in pszemraj/flan-t5-xl-instructiongen 9 months ago

Adding `safetensors` variant of this model

#2 opened 9 months ago by

SFconvertbot

New activity in pszemraj/long-t5-tglobal-xl-16384-booksci-summary-v1 9 months ago

Adding `safetensors` variant of this model

#2 opened 9 months ago by

SFconvertbot

New activity in pszemraj/neuspell-scrnn-probwordnoise 9 months ago

Adding `safetensors` variant of this model

#1 opened 9 months ago by

SFconvertbot

New activity in nvidia/NitroGen 9 months ago

Performance bad in game client

6

#6 opened 9 months ago by

wkruan

New activity in allenai/Olmo-3.1-32B-Instruct 10 months ago

use_cache set to false?

👀 1

#4 opened 10 months ago by

pszemraj