nlp, transformers and adapter

AdapterHub: New Kid on the Block for Transfer Learning

Introduction First, there was a BERT, at least all of this started with it. It is a general-purpose language model, once pre-trained for different languages and in different size variations. If you wanted to use it for some specific task, you should fine-tune it in a way that you take ... Read More
about gpt-3 again

About GPT-3. Again.

There is a lot of hype about GPT-3 since it appeared. Everybody was so excited about its results. It doesn’t need fine-tuning for some specific task, which is quite an impressive result. Also, it is very good at writing poems, writing code, and SQL queries at the same time. Isn’t ... Read More

Abot Vaex: The Best Datarames Library

I’m interested in a fast and effective Dataframes library for a while. Pandas is defacto data frame library of choice in Python and Data Science, having in mind the easy of its use and available features. However, most of the time it is used for data previewing, analysis, and the ... Read More
Chatbot

Facebook Blender

I’m playing a lot these days with chatbots. I fount this link interesting: About my own experience with Blender: ... Read More
JavaScript Programming

JavaScript for DataScience

Like it or not, JavaScript is here to stay. Tensorflow models can be accessed by JavaScript, so do Torch ones. And node.js is something that allows to use JavaScript in command line. So, deal with it, on the proper way, and take the best of JavaScript. Of course, you don’t ... Read More
Eigenvectors and eigenvalues

This is So Cool :-)

This is so cool so I couldn’t resist to sharing it with you: In short: Quantum Mechanics physicists found clues for properties for Eigenvectors and values still unknown for the Math. Clear clue how much of processing power is put into quantum mechanics and analyzing its experiment results. ... Read More
Size does Matter

Size Does Matter

Introduction In a word of NLP and language models, size does matter. Literally, the bigger is better. Since the appearance of transformers on the NLP horizon, they became a de facto synonym for successful language model implementation, shadowing usage of recurrent neural networks, and LSTM. NLP got their equivalent of ... Read More
Interesting AI Startups

Unknown but Innovative Cool and Scarry

AI innovation is not only AI research. And Google, DeepMind, Facebook, and OpenAI are not the only AI innovators. Innovation is also to find exciting use-cases where nobody looked for them yet, and scale them beyond imaginable. This article is about a few of the unknown, yet innovative companies with ... Read More
AI Programming Heroes

My AI Programming Heros During Corona Days

One Long Introduction Currently I’m working on Question and Answering system based on BERT. Some online resource for it: Since it’s announcement and open-sourcing, many optimizations and variations appeared. There are smaller but faster versions optimized for memory footprint and speed for mobile devices. Also, after some research, some variations ... Read More