view article Article ChatML vs Harmony: Understanding the new Format from OpenAI 🔍 kuotient • Aug 9, 2025 • 59
view post Post 10830 THIS IS CRAZY! THE MODEL ON THE IMAGE(Supra-50M-Reasoning) answered correctly and its QUANTIZED IN 2BIT! THE RESPONSE IS CORRECT, IN A 15MB SIZE FILE! See translation 14 replies · 🔥 29 29 👀 9 9 🧠 3 3 😔 1 1 + Reply
ZeroGPT Classifier Attack Collection Models and datasets meant to crack the ZeroGPT.com classifier • 4 items • Updated about 1 month ago • 2
TeichAI/Qwen3-4B-Thinking-2507-Claude-Haiku-4.5-High-Reasoning-Distill Text Generation • 4B • Updated Dec 22, 2025 • 9 • 1
DFlash Collection Block Diffusion for Flash Speculative Decoding • 22 items • Updated 1 day ago • 130
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled Image-Text-to-Text • 28B • Updated Apr 6 • 95.9k • • 2.88k