🏝️ On Vacation

DedeProGames PRO

DedeProGames

P(doom) <0.1%

·

AI & ML interests

Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher

Recent Activity

upvoted a collection 8 minutes ago

new activity 12 minutes ago

BananaMind/README:Remove DedeProGames from README

new activity about 7 hours ago

AxiomicLabs/GPT-S-5M:Hmmm

View all activity

Organizations

upvoted a collection 8 minutes ago

SupraNeo

SupraNeo: The subfamily of the Supra models, delivering intelligence in a compact size • 1 item • Updated 8 minutes ago • 3

upvoted a changelog 7 days ago

Hugging Face Changelog

P(doom) on user profiles

7 days ago

• 345

upvoted a collection 12 days ago

LowOnMind

LowOnMind: Small decoder-only models trained in small amount of tokens • 4 items • Updated 12 days ago • 1

upvoted a collection 13 days ago

Wisp

Wisp: small Llama-style base models trained from scratch on educational text and code. • 2 items • Updated about 21 hours ago • 1

upvoted a changelog 17 days ago

Hugging Face Changelog

Live resource usage on Jobs

17 days ago

• 208

upvoted 2 changelogs 18 days ago

Hugging Face Changelog

Granular Feature Access

Aug 12

• 422

Hugging Face Changelog

Preview LeRobot Episodes

18 days ago

• 77

upvoted an article 23 days ago

Article

Layer-Feedback Transformer (LFT)

Banaxi-Tech

•

23 days ago

• 6

upvoted an article 25 days ago

Article

When Benchmark Numbers Become Marketing

DedeProGames

•

25 days ago

• 7

upvoted a paper 27 days ago

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

Paper • 2601.10332 • Published Jan 15 • 33

upvoted a collection 29 days ago

Experimental Decoder-Onlys

Some experimental decoder-onlys made by me for research • 4 items • Updated about 21 hours ago • 2

upvoted an article 29 days ago

Article

How Did We Get Here?

NILKNARFGonzo

•

30 days ago

• 8

upvoted an article about 1 month ago

Article

Lorem Ipsum

GGUFGuy

•

Sep 10

• 4

upvoted a collection about 1 month ago

Kiyo

Kiyo: State-of-the-art models trained from scratch on vast amounts of web tokens, educational text, and code. • 2 items • Updated about 13 hours ago • 2

upvoted a paper about 1 month ago

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 61

upvoted 3 collections about 2 months ago

DynamicMind

DynamicMind: a family of lightweight models trained from scratch on diverse datasets. • 3 items • Updated about 21 hours ago • 2

LowOnMind

LowOnMind: Small decoder-only models trained in small amount of tokens • 4 items • Updated about 21 hours ago • 2

Qwen3.8

4 items • Updated Aug 13 • 572

upvoted 2 articles 2 months ago

Article

DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)

DedeProGames

•

Aug 11

• 22

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

+4

burtenshaw, danielhanchen, shimmyshimmer, mlabonne, davanstrien, evalstate

•

Feb 20

• 113