Hi, I'm syoka
import asyncioasync def journey():while True:await keep_learning()await take_action()await deep_thinking()asyncio.run(journey())
Tech Stack
最新文章
探索我最新的想法和见解
30岁的人生自传小结
从刚出校园的职场小白,到如今已进入中年人序列的我来说,想对自己过去10年做一个简单小结。
AI Engineer Portraits
Recently, I had a conversation with DongGe, a senior engineering architect. Together, we summarized the key capabilities required for four major AI-era roles: Algorithm, Data, Engineering, and Architecture. This framework can serve as a reference for job design and personal development. Feel free to add your thoughts or reach out to me directly.
Large Model Compression Techniques
Let's first introduce the background of the era of large model compression, starting from GPT3, the magnitude of the weight parameters of the model has gradually risen, and the requirements for hardware have become higher and higher. Taking GPT3 as an example, under FP16 precision, 325G of memory is also required, and if the specification of A100 80G is taken as an example, at least 5 sheets are needed. Therefore, for mobile embedded devices running on limited arithmetic, to ensure that the model performance is acceptable,
技术面试的思考
这是我对24年的面试过程进行了一轮总结,并将里面不断完善我自己的理解