Wisp: small Llama-style base models trained from scratch on educational text and code.
DedeProGames PRO
DedeProGames
AI & ML interests
Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher
Recent Activity
updated a dataset about 2 hours ago
DedeProGames/lm-tetris-arena-results new activity about 3 hours ago
SupraLabs/supra2-img-demo:Please private thos space updated a Space about 3 hours ago
SupraLabs/Supra-IMG-StudioOrganizations
Kiyo: State-of-the-art models trained from scratch on vast amounts of web tokens, educational text, and code.
LowOnMind: Small decoder-only models trained in small amount of tokens
-
SLM-Archive/LowOnMind-8M
Text Generation • 8.06M • Updated • 741 • 2 -
SLM-Archive/LowOnMind-5M
Text Generation • 4.92M • Updated • 375 • 1 -
SLM-Archive/LowOnMind-1M
Text Generation • 985k • Updated • 388 • 3 -
SLM-Archive/LowOnMind-300k
Text Generation • 297k • Updated • 455 • 4
Small and Efficient Chess Models
GPT-U: small Llama-style base models trained from scratch on web, educational text and code, with fully open scripts, logs and evals.
DynamicMind: a family of lightweight models trained from scratch on diverse datasets.
Some experimental decoder-onlys made by me for research
-
SLM-Archive/NanoDex-Test-500K-200M
Text Generation • 492k • Updated • 962 • 1 -
SLM-Archive/NanoDex-1M
Text Generation • 1.06M • Updated • 939 • 1 -
SLM-Archive/Overaddicted-500K
Text Generation • 492k • Updated • 1.2k • 1 -
DedeProGames/Kiyo-Diffusion-135M
Text Generation • 0.1B • Updated • 64 • 1
Experimental medical model based on Qwen2.5 Family
Wisp: small Llama-style base models trained from scratch on educational text and code.
GPT-U: small Llama-style base models trained from scratch on web, educational text and code, with fully open scripts, logs and evals.
Kiyo: State-of-the-art models trained from scratch on vast amounts of web tokens, educational text, and code.
DynamicMind: a family of lightweight models trained from scratch on diverse datasets.
LowOnMind: Small decoder-only models trained in small amount of tokens
-
SLM-Archive/LowOnMind-8M
Text Generation • 8.06M • Updated • 741 • 2 -
SLM-Archive/LowOnMind-5M
Text Generation • 4.92M • Updated • 375 • 1 -
SLM-Archive/LowOnMind-1M
Text Generation • 985k • Updated • 388 • 3 -
SLM-Archive/LowOnMind-300k
Text Generation • 297k • Updated • 455 • 4
Some experimental decoder-onlys made by me for research
-
SLM-Archive/NanoDex-Test-500K-200M
Text Generation • 492k • Updated • 962 • 1 -
SLM-Archive/NanoDex-1M
Text Generation • 1.06M • Updated • 939 • 1 -
SLM-Archive/Overaddicted-500K
Text Generation • 492k • Updated • 1.2k • 1 -
DedeProGames/Kiyo-Diffusion-135M
Text Generation • 0.1B • Updated • 64 • 1
Experimental medical model based on Qwen2.5 Family
Small and Efficient Chess Models