Sublime

China just dropped a new model. ByteDance Doubao-1.5-pro matches GPT 4o benchmarks at 50x cheaper — $0.022/M cached input tokens, $0.11/M input, $0.275/M output — 5x cheaper than DeepSeek, >200x of o1 — 32k + 256k context — sparse MoE... See more

Structured information extraction from PDFs https://t.co/HP5fHfO77Z

PDF data extraction tool https://t.co/pNHHgUJ8Km

ChamathAI took me half as long to build as TopGPT & performed 2x better. ⭐️600+ people have stared the repos that made it possible. How I built it, what I learned, and an updated guide to fine-tuning a chatbot ⬇️ https://t.co/h6Q8Q3pzQU

Convert PDFs to machine-readable formatslike markdown or JSON for easy data extraction https://t.co/e6H7TSkqmM

PDF processing toolkit for LLMs https://t.co/ENTHDjR7VY

"regular people don't fine-tune VLMs" but wtf not? - skill gap - high fine-tuning costs - lack of standards and unified approaches over the past few weeks I've been working on maestro - streamlined tool for VLM... See more