Maarten Grootendorst has released his new book "Hands-On Large Language Models" with over 250 color visuals. I bought it! Meanwhile, the AIatMeta team unveiled SAM 2, a powerful computer vision model for image and video segmentation, optimized for Mac and iPhone. Also coming is Vchitect-2.0, a new text-to-image engine that promises great things.
FutureHouse launches PaperQA2, a game-changing AI agent for scientific research. This tool can find, analyze and synthesize scientific papers, outperforming even experienced researchers. Among its capabilities: citation exploration, information extraction, and formulation of accurate answers.
Autonomously hosting an LLM such as the 70-billion-parameter LLaMA 3.1 may seem challenging, but with the right hardware optimizations such as appropriate GPUs, quantization techniques and sharding, it can be done without spending a fortune. Hybrid cloud solutions offer a good trade-off between cost and flexibility while maintaining control over the data