Dika Alkautsar's picture

Dika Alkautsar

alkautsardika

·

deight07

AI & ML interests

None yet

Recent Activity

reacted to AdinaY's post with 😎 6 days ago

Moonshot AI 月之暗面 🌛 @Kimi_Moonshotis just dropped an MoE VLM and an MoE Reasoning VLM on the hub!! Model:https://huggingface.co/collections/moonshotai/kimi-vl-a3b-67f67b6ac91d3b03d382dd85 ✨3B with MIT license ✨Long context windows up to 128K ✨Strong multimodal reasoning (36.8% on MathVision, on par with 10x larger models) and agent skills (34.5% on ScreenSpot-Pro)

reacted to onekq's post with 🚀 6 days ago

We desperately need GPU for model inference. CPU can't replace GPU. I will start with the basics. GPU is designed to serve predictable workloads with many parallel units (pixels, tensors, tokens). So a GPU allocates as much transistor budget as possible to build thousands of compute units (Cuda cores in NVidia or execution units in Apple Silicon), each capable of running a thread. But CPU is designed to handle all kinds of workloads. CPU cores are much larger (hence a lot fewer) with branch prediction and other complex things. In addition, more and more transistors are allocated to build larger cache (~50% now) to house the unpredictable, devouring the compute budget. Generalists can't beat specialists.

reacted to hesamation's post with ❤️ 6 days ago

Google published a 69-page whitepaper on Prompt Engineering and its best practices, a must-read if you are using LLMs in production: > zero-shot, one-shot, few-shot > system prompting > chain-of-thought (CoT) > ReAct LINK: https://www.kaggle.com/whitepaper-prompt-engineering > code prompting > best practices

View all activity

Organizations

None yet

models

None public yet

datasets

None public yet