Machine Learning
1297 Threads
A model is useless if it's sitting in your Jupyter Notebook! Today, we learn how to deploy any machine learning model in 5 easy steps! ๐ A Thread ๐งต๐ https://t.co/aSg8ch1HfS
Implementing Linear Regression from scratch ๐งต Problem Statement: Model the demand for shared bikes with the available independent variables Libraries used > pandas > numpy > seab...
Open AI just released their most powerful tool yet. The Code Interpreter. Here are 10 insane examples I've found: https://t.co/nqiJYK4v3h
Our team at @MosaicML has been working on releasing something special: We're proud to announce that we are OPEN SOURCING a 7B LLM trained to 1T tokens The MPT model outperforms AL...
GPUs are becoming scarce. Everyone is now training and deploying ML models ๐ฆพ Deploy your ML models on CPUs with the same performance as a T4 GPU. Here's how ๐ฅ --A Thread-- ๐งต 1/6
@abacaj using the same LLM to be many times bigger 4. Distill a smaller model 5. When a new request comes if it falls into the cluster we found use the smaller model 6. Sample r...
How to turn an ML notebook into a real-world ML app? (using only Python and MLOps) ๐งตโโโ
Top YouTube Channels & Websites to Learn WEB-DEV, Cyber Security, AI/ML,DS & Algo,Blockchain, App development , DevOps A Thread ๐งต https://t.co/Y0xfhXePeO
K-Nearest Neighbours (KNN) is a simple yet powerful ML algorithm! Today, we clearly understand & implement KNN from scratch! ๐ฅ Let's go! ๐งต๐ https://t.co/ciGcZNyA8P
Top ML Papers of the Week (April 24 - 30): - AudioGPT - Track Anything - Agents Learn Soccer Skills - Harnessing the Power of LLMs - Scaling Transformer to 1M tokens - A Cookboo...
I have been writing data science and ML blogs for more than 1.5 years now๐ Many articles and blogs help 1000s of people to get crucial insights into the data science industry๐ญ He...
Imbalanced datasets can cause real trouble. But undersampling and oversampling can help. Here is how they work ๐ฝ 1/8 https://t.co/UQ2Dh5Pjl3
Fine tuned GPT-2 a 1.5B model from 2019 outperforming Alpaca LLaMA a 7B model from 2023... https://t.co/Gode5F15aq
Junior data scientists stay inside Jupyter. Senior data scientists go beyond ๐ Let me explain โ
Andrew Ng is one of the most recognized researchers in the world. In 2017, a team he led published a paper with a huge mistake. 11 days later, they had to publish a correction. H...
Errors in Linear regression โ ๏ธ How do we know if our predictive model is good or bad? I will explain ๐ฝ https://t.co/Rzezagfofq
If you don't know how to use ChatGPT to Analyze Data you are behind. Don't let someone take over your Job. Let me show you how you can Use ChatGPT to Analyze Data. -Thread-
ChatGPT Cheat Sheet: This is one of the easiest and most effective ways to use ChatGPT. Acting as a (ROLE) perform (TASK) in (FORMAT) ๐ https://t.co/dPAtDPY0kT
ChatGPT will never work for trading. That's what I thought 3 weeks ago. Then I spent 35 hours in the GPT-4 rabbit hole. These 6 blogs show you what you can do. And it doesn't t...
Large Language Models (LLMs) are notoriously bad at solving reasoning-based tasks. However, we can drastically improve their reasoning performance using simple techniques that requ...
Linear Regression is a powerful tool in machine learning. Read this ๐งต for the simplest explanation of Linear Regression. ๐ฝ https://t.co/cCD8tKCa8b
Advice for ML beginners ๐ก โ The end goal of any ML model is to improve a business metric. ๐ผ โ And deploying an ML model to localhost DOES NOT move any business metrics. ๐ต Here a...
This is a useful recent talk on why LLMs hallucinate. It seems that fine tuning can teach the model to hallucinate more if that knowledge was not previously seen before during trai...
How to build *TruthGPT*? I listened to a talk by the legendary @johnschulman2. It's densely packed with lots of deep insight. Key takeaways: - Supervised finetuning (or behavior c...
