🔄 In a Training Loop

ouasdg

ouasdg

·

AI & ML interests

None yet

Recent Activity

reacted to anakin87's post with ❤️ about 3 hours 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 7 days ago

datasocial/tiktok-5.6B-videos

liked a model 12 days ago

Lightricks/LTX-2.5-22b-IC-LoRA-SDR-To-HDR

View all activity

Organizations

ouasdg 's models 15

ouasdg/dirt

ouasdg/vilex

ouasdg/midilm

Updated Nov 17, 2025

ouasdg/kontext-nf4-depth-lora

Updated Sep 22, 2025 • 14

ouasdg/hertz

Updated Apr 18, 2025

ouasdg/sd-ft

Updated Nov 11, 2024

ouasdg/ttstest

Updated Mar 27, 2024

ouasdg/tinyllama-pedia

Text Generation • 1B • Updated Jan 29, 2024 • 14

ouasdg/phi-pedia

Text Generation • 1B • Updated Jan 25, 2024 • 23

ouasdg/gpt2-pedia

Text Generation • Updated Jan 23, 2024 • 16

ouasdg/distilbert-imdb

Text Classification • 67M • Updated Dec 18, 2023 • 7

ouasdg/gpt-draw

Text Generation • Updated Nov 9, 2023 • 12 • 2

ouasdg/redpj3B-lora-int8-alpaca

Updated Sep 26, 2023 • 11

ouasdg/brokenizer

Updated Sep 1, 2023

ouasdg/fokentoken

Updated Jul 27, 2023