Here you will find the basic theory of Machine Learning and examples of the implementation of specific ML algorithms - in general, this is just the thing to brush up on your knowledge before the interview.
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
This is a course on neural networks from the very basics, perhaps the best on the entire Internet.
The course is a series of YouTube videos in which Karpathy shows how to design and train neural networks.
All these results are written in Jupyter-Notebooks, you can download them and experiment
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
docker run --ipc=host --shm-size=512m --gpus all -it nvcr.io/nvidia/pytorch:24.02-py3
pip install megatron_core
pip install tensorstore==0.1.45
pip install zarr
Megatron-Core is a self-contained, lightweight PyTorch library that contains everything you need to train Transformers.
Offers a large collection of GPU techniques for optimizing memory and calculations, uses a lot of developments from Megatron-LM and Transformer Engine.
Megatron-Core provides flexibility for developers and makes it easy to develop their own LLM framework on NVIDIA computing infrastructure.
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
This media is not supported in your browser
VIEW IN TELEGRAM
┌
└
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
A collection of completely free neural nets on hugginface
You can use them to do cool photo upscaling, remove backgrounds, edit images and more.
All the models are free and opensource here: huggingface.
🌐 http://t.me/codeprogrammer ✅️
You can use them to do cool photo upscaling, remove backgrounds, edit images and more.
All the models are free and opensource here: huggingface.
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
🤖 Mistral has released a neural network that knows more than 80 programming languages. Codestral surpasses such giants as Llama-3 and CodeLlama, as well as... GPT-4o, and yet weighs three times less!
This model knows how to write and improve code, suggests the best solutions to problems and even knows design patterns. You can connect it to your projects via API or just use it in VS Code. For olds: the neural network even knows Fortran and COBOL.
Use it here or directly in your browser here.
#GPT4 #AI #PYTHON
🌐 http://t.me/codeprogrammer ✅️
This model knows how to write and improve code, suggests the best solutions to problems and even knows design patterns. You can connect it to your projects via API or just use it in VS Code. For olds: the neural network even knows Fortran and COBOL.
Use it here or directly in your browser here.
#GPT4 #AI #PYTHON
🌐 http://t.me/codeprogrammer ✅️
We’ve carefully selected the best YouTube channels for diving deep into AI:
1. Sentdex: Python and machine learning tutorials.
2. Two Minute Papers: Quick AI research summaries.
3. Siraj Raval: Accessible AI education.
4. TensorFlow: Tutorials and demos on this open-source library.
5. Lex Fridman: Interviews with AI experts.
6. Matt Wolfe: AI news, reviews, and tutorials.
7. AI Explained: Simplifying complex AI concepts.
8. DeepLearning.AI: Courses by Andrew Ng.
9. Yannic Kilcher: Practical AI tutorials.
10. Data School: Data science and machine learning tutorials.
Check out these channels for more!
#AI #MACHINELEARNING #PYTHON
Please open Telegram to view this post
VIEW IN TELEGRAM
By the way, here are some of them:
sample.txt file to the .tar.gz archive:import tarfile
with tarfile.open('sample.tar.gz', 'w:gz') as tar:
tar.add('sample.txt')
import difflib
diff = difflib.ndiff('one\ntwo\nthree\n'.splitlines(keepends=True),
'ore\ntree\nemu\n'.splitlines(keepends=True))
print(''.join(diff))
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM