The ability for LLMs to learn how to use tools seems to emerge at around 775M parameters. In a study where they gave this learning capacity to LLMs of various size , the authors found that LLMs could only use them effectively when they had a size of 775M and above.
Hi everyone, I hope that you are all doing great this week! I'm hosting an intro to Python workshop this Friday at 14h EST on Google Meet, it follows this overview lecture on data science I gave at the end of February: For this workshop series, there is no pre-requisite,
Yesterday, the group behind another impressive model called Latent Diffusion Model release the full source code along with the trained weight of their model!
The answer is yes.
A lot of people want to learn machine learning these days. But the daunting bottom-up curriculum that most ML teachers propose is enough discourage a lot of newcomers.
AI's are making waves once again fueled by consciousness claim hype. Before we head into another AI winter, let's try to reduce the hype (just enough to still get funding and calm everyone expectation).
Some concepts in machine learning may at first glance look extremely opaque and difficult to grasp. Yet, most are pretty accessible and simple. However, they are usually clouded by terminology you don't understand or heavy math notations. When you are faced with one such concept that is stumping you: 1.
Being able to quantify the amount of information in a sequence is important in many fields and applies to many data set. Shannon Entropy is one such information theory method that given a random variable and historic about this variable occurrence can quantify the average level of information!
Generating art with AI is surprisingly easy! Here are 5 links to get you started!
This week I'll be sharing 5 books on Machine Learning that I highly recommend. No particular order, I read all of them and they were truly helpful throughout my PhD!