Distill — It has some pretty nice articles with nice visualization. The Gradient The Gradient is a digital magazine covering research and trends in artificial intelligence and machine learning. From the official website LessWrong LessWrong and Artificial Intelligence For several reasons, LessWrong is a website and community with a strong interest in AI and specifically…

From the original paper we know that base has about 65M parameters, while the big has 213M parameters. The question is how to compute those number of parameters? How to computer number of parameters?

Explore GPT3 alternatives — This article is not talking about what is GPT1/2/3. If you don’t know those models yet, you can first check other online blogs and videos to know what those models are doing first. Here is a quick summary (Also needs the read knows what is transformer): To be short, GPT1/2/3…

hello world! — Install from terminal[1] curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

A nice discussion and examples can be found in [1]. The quick answer from the top voted of [1] is: Python’s “parameter evaluation strategy” acts a bit different than the languages you’re probably used to. Instead of having explicit call by value and call by reference semantics, python has call…

Original I thought the current path is the path where you run the python code. Such as python ./subfloder/XX.py, then the current path will be the previous path of subfloder. However, I am wrong. It should be the folder of the XX.py which is the subfolder. …

Problem The iphone storage is full and my iphone 13 got stuck on the home screen when asking me to input the passcode. Solution Previously, I had a similar issue and when I went to Apple store, they reset my iphone and of course all unsaved images and videos lost :( This…

Which testing tools that we can use for python? As a software engineer, it is a common practice to add test cases for your software and program. General, we need Unit Tests and Integration Tests. [5] gave a pretty clear explanation. We have 3 ways to run python tesing. unittest nose or nose2 pytest Originally, I was using pytest, it is pretty convenient. However, I got quite a lot of Moudular import error, especially in the docker environment. So I switched to unittest and there is no issue. If you wanna to know how to use the “unittest”, please check [5].

A reinforcement learning practice — What is stable_baseline3 ? stable_baselines3 is a Reinforcement Learning Implementation package developped by awesome researchers and engineers from Germany, France, USA and Finland as you can discover from the author list based on the paper: