🔄 In a Training Loop

ouasdg

ouasdg

·

AI & ML interests

None yet

Recent Activity

liked a model about 9 hours ago

divagr1925/Qwen3.5-4B-Qwenputer

reacted to anakin87's post with ❤️ 12 days ago

I made a 1.1M ModernBERT encoder play Doom in real time on a CPU Some time ago, VAGO Solutions released SauerkrautLM-Doom-MultiVec-1.3M, a tiny model trained to play Doom Defend the Center scenario from 31k human gameplay examples. My first thought: cool! I love both Doom and Small Language Models. Then another idea: I bet I can do better :-) What I did? - evaluated the original model and found it's better than reported - changed a bit the architecture - generated SFT data with a scripted oracle - SFT + PPO refinement on consumer hardware Got a smaller, faster and killer model Can even fit a floppy with int8 quantization 💾 Watch it play/read the article: https://huggingface.co/spaces/anakin87/tiny-doom-defender

liked a dataset 19 days ago

datasocial/tiktok-5.6B-videos

View all activity

Organizations

ouasdg 's datasets 12

ouasdg/frampton

Viewer • Updated Jan 21 • 8.01M • 10

ouasdg/pedia

Updated May 24, 2025 • 12

ouasdg/test

Updated Mar 26, 2025 • 58

ouasdg/yt-comments

Updated May 4, 2024 • 23

ouasdg/vids-100k

Updated Apr 6, 2024 • 439

ouasdg/discak-100k

Viewer • Updated Jan 24, 2024 • 109k • 13

ouasdg/discak-small

Viewer • Updated Jan 22, 2024 • 23.4k • 11

ouasdg/Thumbs-1M

Viewer • Updated Jan 6, 2024 • 1.01M • 11 • 1

ouasdg/leerik-verses

Viewer • Updated Oct 22, 2023 • 14.1M • 13

ouasdg/coco-encoded

Viewer • Updated Oct 18, 2023 • 118k • 14

ouasdg/cc3m-morepieces

Viewer • Updated Sep 20, 2023 • 2.84M • 15

ouasdg/laion-vqgan-f16

Viewer • Updated Sep 5, 2023 • 4.46M • 37