Today I learnt: 1. Fine-tuning BERT with some layers frozen (82.1% accuracy achieved) 2. How to create a report on Weights & Biases and how to compare results from different projects 3. CS229 Lecture 1: Introduction to linear algebra. Covered the math behind ml. Lecture 1 focused on

mlx-vlm v0.4.3 is here 🚀 Day-0 support: 🔥 Gemma 4 (vision, audio, MoE) by Google DeepMind 🦅 Falcon-OCR + Falcon Perception by Technology Innovation Institute 🪨 Granite Vision 4.0 by IBM Research New models: 🎯 SAM 3.1 with Object Multiplex by Facebook 🔍 RF-DETR detection & segmentation by

x.com/i/article/2039…

Brain is fuming, so many math equations. But today I’m learning about one of my favourite topics: Tensor decomposition! 😁 I did my bachelor’s thesis on this, titled ‘Low rank compression of CNNs using tensor decomposition methods’

Today I learnt: 1. Quadratic forms and definitiveness - How the eigen values of the symmetric matrix A determines if they are positive, negative or indefinite 2.SVD and EVD - Decomposition of matrices focusing on singular and eigen value decomposition - Looked at the formulae

Today's lecture was very information dense and didn't get to go through the BERT paper again as I intended to (make the paper breakdown). Making this P1 for tomorrow and will also revisit the concepts again to master them before continuing

Out of curiosity, how many times do you read a research paper before implementing it?

A paper a day, keeps the doctor away

This is such a great list of papers to start with. I got some questions on where to begin and I would say this is a great starting point if you’re interested in LLMs and Transformers

These are the books I keep going back to as someone who is interested in LLMs and Transformers. I reach for these gems a few times a day. Book 1: Natural Language Processing with Transformers by Lewis Tunstall Leandro von Werra Thomas Wolf Book 2: Hands On Large Language Models bu

First time lapse of Gym Geeks 🤣 Where wifey and I train hard, and maybe discuss latest updates in the AI space. Maziyar PANAHI

Fine-tuning transformers used to feel intimidating to me, but it doesn't have to be. I just published a beginner-friendly guide to fine-tuning BERT using Hugging Face, where I walk through: - What fine-tuning actually is - A quick intro to BERT - A full code walkthrough on the

My medium account has been suspended!! Oh my💔How do I fix this?!!

Let me implement a paper! I could potentially win a max mini. How exciting😇

And it happens on the day I decide to write an article💔💔

Any tech events in Poland🇵🇱 this April? I would love to attend and make new acquaintances

Wheeeew!! We are back! Medium account has been reactivated