Sublime

NEW: SoTA OCR model - Apache 2.0 licensed based on Qwen 2.5 VL 🔥 https://t.co/YhDbwyHCvP

450 USD is all you need to train YOUR OWN O1 🌟

“I have learned this of myself, that I cannot do without people and I cannot do without stretches of sustained isolation.”

> We find that LLMs’ intelligence [...] almost linearly correlates with their ability to compress external text corpora > compression efficiency [...] serves as a reliable evaluation measure that is linearly associated with the model capabilities IQ for LLMs just dropped https://t.co/B9UOeLctRS