Abu Sufyan

Machine Learning Engineer | YouTuber
~Interested in robotics & autonomous vehicles

[Kirk Borne @KirkDBorne]

Many PDFs of brilliant #MachineLearning cheatsheets cover the content of Stanford's CS229: https://t.co/Rb6OJLvkza

Explore them in detail at Github: https://t.co/1rjJ5g2HHp by @shervinea and @afshinea <= #DigitalTwins??

#BigData #DataScience #DeepLearning #AI #Algorithms

[Abu Sufyan @abusufyanvu]

@swapnakpanda please provide a such order which can lead Generative ai and llms

[ℏεsam @Hesamation]

Stanford just released a new course for this Fall: Transformers & Large Language Models by the Amidi brothers. Three videos are already available for free on YouTube.

SYLLABUS:
> Transformers (tokenization, embeddings, attention, architecture)
> LLM foundations (MoEs, types of decoding)
> LLM training and tuning (SFT, RL , LoRA)
> LLM evaluation (LLM/VLM-as-a-judge and best practices)
> Common tricks (RoPE, attention approximation, quantization)
> Reasoning (train/test-time scaling)
> Agentic workflows (RAG, tool calling)

If you already know this stuff, this is a good chance to refresh your mind about some of these topics, and potentially code some techniques from scratch.

Course syllabus and video links: https://t.co/6Io1nitSx3

[Vaishnavi @_vmlops]

AI/ML Engineers don’t skip this!
This Stanford University course is a true gold mine covering everything you need to build and fine-tune LLMs from the ground up

[Abu Sufyan @abusufyanvu]

@elonmuskTN 56

[اردو ورثہ @UrduVirsa]

میں خیال ہوں کسی اور کا مجھے سوچتا کوئی اور ہے
سر آئینہ مرا عکس ہے پس آئینہ کوئی اور ہے

میں کسی کے دست طلب میں ہوں تو کسی کے حرف دعا میں ہوں
میں نصیب ہوں کسی اور کا مجھے مانگتا کوئی اور ہے

عجب اعتبار و بے اعتباری کے درمیان ہے زندگی
میں قریب ہوں کسی اور کے مجھے جانتا کوئی اور ہے

مری روشنی ترے خد و خال سے مختلف تو نہیں مگر
تو قریب آ تجھے دیکھ لوں تو وہی ہے یا کوئی اور ہے

تجھے دشمنوں کی خبر نہ تھی مجھے دوستوں کا پتا نہیں
تری داستاں کوئی اور تھی مرا واقعہ کوئی اور ہے

وہی منصفوں کی روایتیں وہی فیصلوں کی عبارتیں
مرا جرم تو کوئی اور تھا پہ مری سزا کوئی اور ہے

کبھی لوٹ آئیں تو پوچھنا نہیں دیکھنا انہیں غور سے
جنہیں راستے میں خبر ہوئی کہ یہ راستہ کوئی اور ہے

جو مری ریاضت نیم شب کو سلیمؔ صبح نہ مل سکی
تو پھر اس کے معنی تو یہ ہوئے کہ یہاں خدا کوئی اور ہے

سلیم کوثر

[Abu Sufyan @abusufyanvu]

@DimaZeniuk visionary

[Abu Sufyan @abusufyanvu]

@ElonMuskOde Yes

[Soheil Feizi @FeiziSoheil]

Just dropped a 4 hour lecture on "Large Language Models": https://t.co/KI5CJ6OksI

0:00 Basics of language models
2:30 Word2vec
16:27 Transfer Learning
19:23 BERT
1:00:39 T5
1:31:14 GPT1-3
1:53:05 ChatGPT
2:20:03 LLMs as Deep RL
2:53:00 Policy Gradient
3:32:50 Train your own LLM

[Gabriel Peyré @gabrielpeyre]

Oscillations are introduced by polynomial interpolation at equi-spaced grid points. https://t.co/pTNnbKn8kn
https://t.co/VdbqfZguXD

[Abu Sufyan @abusufyanvu]

@Stanford CS229: Machine Learning (Spring 2022) Really cool to see a new iteration of this course. It's a classic ML course from Stanford that has helped tons of students get started with machine learning.

YouTue Lectures: https://t.co/IvbDHthwHU

#MachineLearning

[Sebastian Thrun @SebastianThrun]

Just saw self driving car cut off fire truck

[Abu Sufyan @abusufyanvu]

What is the fundamental building block of a neural network?

[Abu Sufyan @abusufyanvu]

@DobkoMaria @AndrewYNg Lucky!, Wish to meet with sir @AndrewYNg

[Steven Strogatz @stevenstrogatz]

You may know Prof. Gil Strang's famous book "Linear Algebra and Its Applications," or you may have watched his Linear Algebra (18.06) lectures at @MIT on YouTube.

Gil's final lecture will be live streamed tomorrow at 11 am EST. Join the celebration at https://t.co/ExPPnsRW3G

[JJ @JosephJacks_]

Alexander and Ava are superstars! https://t.co/bRdY8YSfnX // @MITDeepLearning

[Trista @Project2501_117]

A big thank you to @elonmusk and @SpaceX for having us out for the launch of Starship! Wow what a sight to see and a force to feel!!! 🚀🚀🚀

[Rumi Chunara @rumichunara]

Beautiful PhD advisor moment as a student graduates and transitions 🌸✨

Congrats @harvineet_singh, strong work during your PhD and look forward to your leadership in machine learning and health going forward!

[Logan Kilpatrick @OfficialLoganK]

Despite what you see here on Twitter and all the hype, GPT-5 is not being trained right now, nor will it be for some time.

GPT-4 took 6 months post training to ensure a safe and aligned model. This is likely to increase for future models.

TLDR; focus on GPT-4!