Video

its really hard for me to understand the documentation and function of binning thanks sir for this useful video!

is there any video about functions when we have to do functions

Nice one

I have been binge watching all the series. Where is episode 4? :( I really wanted to learn about the dashboards. Great work either way!!

which browser are you using?

Even After 3 year ❤

Hi, How did you add your device with your laptop please?

Hey any news on when Episode 4 of Learn Data Analysis with Python is coming? The project is great and I’d love to finish it.

Are you familiar with the DoorDash driver app? Is it possible to scrape data from that using MITM. Specifically, what I’m hoping for is a way to scrape all of my earnings from my time as a DoorDash driver (orders, stores, dates, base pay & tip). I’m not sure if you’ll even see this, but thanks in advance. I really appreciate these videos. Excellent content!

Thank you so much for this incredibly helpful video on web scraping! Your explanations were clear and easy to follow, and the examples you provided made it much easier to understand. keep up!

wonderful explanation - thank you!

I interpreted ollamas version as correct. It states a few things there. It says think about it. You placed the plate on top of the cake which means the cake is now on the plate, this is true if cake transferred to the plate when you placed the plate on top of the cake which would happen in real life. We're also assuming the cake has icing icing is sticky bits of cake stick to the icing that stick to the plate. It also very specifically stated in it's next paragraph, (on the plate) meaning the cake that's stuck to the plate is currently located.

does it have to be an online link or can send it an image from my own machine?

I get nothing but gibberish output when I install it and run ollama run llama3 on my M3 Max MBP and ask "Who are you?"

After completing this course, are we truly able to make money with python?

For the "unsupported" machines LMstudio is the solution. Download the "model" and choose Llama3-whatever & go. I have a very high powered machine, but since it was a server it doesn't have AVX2, which most model loaders need.

Binge watching your channel. I’m newish to Python. Looking primarily at what you’re able to achieve here. I use a browser but that is as far as I go. To enable me to understand more which paths shall I add to my studies, so that I can understand more regarding working with the inspect and developer tabs. Would adding to understand html, Python requests, pandas be sufficient. Essentially I’m if I was to find a course that covers how you understand websites and the inspect and developer tab views, what broad subject would one look for?

The name has nothing to do with the content at all. Where’s the installation process, which are the recommended hardware prerequisites, where’s Linux and where’s Windows. What was the initial sense of this video?

Thank you for being direct, clear, and straight to the point.

I didn't know Matt Walsh was a programmer.

Hey Man you are one of the best, you always provide clear explanation to what's going on unfortunately there is not much video from you, I wish you can create a series on data analysis from start to end you are a very valuable resource to the community, keep going you are the best🔥

Can remember faces ?

THANK YOU!!! This is sooooo helpful

is this llma3 or llma3:instruct?

funny when I tested it out, chatgpt got it wrong. I used llama 3 uncensored version dolphin and It got it right then on the explanation it hurts itself in its confusion lol Chatgpt: "The cake is in the kitchen. When you placed the plate on top of the cake in the dining room and then picked up the plate and took it into the kitchen, you effectively moved the cake into the kitchen along with the plate." >can you explain how did you solved this problem? "Certainly! Let's break it down step by step: You start in the dining room, where the cake is located on the table. You place a plate on top of the cake in the dining room. At this point, the cake is still in the dining room, but now it has a plate on top of it. Then, you pick up the plate with the cake on it and take it into the kitchen. Now, both the plate and the cake are in the kitchen. So, although the action of placing the plate on the cake initially occurred in the dining room, by moving the plate with the cake on it into the kitchen, you effectively moved the cake into the kitchen as well. Therefore, the cake is currently in the kitchen." Llama3dolphin: " The cake is currently in the dining room." >can you explain how did you solved this problem? "Sure! When you told me that there's a cake on a table in the dining room, and then later mentioned that you moved the plate (with the cake still underneath it) to the kitchen, I used deductive reasoning. Initially, the cake was in the dining room because you put a plate on top of it there. Then, when you moved the plate into the kitchen, the cake went with it, as it was still under the plate. Therefore, the cake is now in the kitchen."

Great content 👍. It's very explanatory and easy to follow along

There is a problem and when you close the terminal and when you open it again it gonna forget the last chat and information

Thanks for the video. Do you know if llama 3 has support for multiple gpus? Hoping it has support for Intel Arc cards as they are cheap and I already have three of them. Might have to get a bunch more if I get it working ;] I've seen Network Chuck here on snoozetube where he got multiple gpus working in llama, looks like it can sense multiple gpus. I get bombarded with advertisements for Nvidia H100 clusters and I'm seeing that just one H100 costs $43,000 on amazon. People are going to find another way besides Nvidia gpus and everyone should start looking at setting up AI locally in their homes. czcams.com/video/d8oVTKG39U8/video.html

Can you please make a tutorial on how to download data from a local sales data software by setting the time period from the software? It'd be very very helpful. TIA!

Just installed this on a Linux box - and wow, this one is great~

Ohh wow wow wow easy:))) thanks for video. Very interesting actually

What about backtick

Love your content man, keep it up❤

was this ever continued? I would be interested to build such a playground

When you ask only for one letter response the model doesnt have time/space for thinking it through.. And also when you write the "please provide a one latter answer" AFTER then the last prompt is provide one letter a or b so small model will get confused and forget about the first part - maybe try to provide formating prompt at begining then pose question 🙂 keep digging

I thought this is what function calling is for?

As a human I'd instinctivelly answer that the cake technically is in both rooms since in most cases some pieces of the cake would stick under the plate. Thought it's an overly technical point since some frosting/cream wouldn't constitute a cake. Lateral thinking is intersting in the context of the LLM. I'd be very curious on the path the prompt takes in the model latent space and what "node(s)" is/are at fault for the mistake.

I’ve seem historical errors in Llama3…

Good

Try the rabbits in the garden exercise: There are two rabbits in the garden. In the garden is a whole. the first rabbit falls in the hole. How many rabbits are left in the garden? response should be still two because the hole is also in the garden. You can give the llm an second chance by explain the hole is also in the garden and that therfore both rabbits are in the garden. Now you tell it that the second bunny also falls in to that hole that is in the garden. It should responds , that both rabbits are in the garden.

I also tried this model. It would often hallucinate and print random letters in a repeating pattern over and over again

Why are they being compared to GPT 3.5 rather than 4?