@rishabh16_ @marksaroufim Visual diagrams for all ops (where applicable) would significantly cut down the time it takes to understand them. Same goes for many high level modules/ tutorials as well
English
Sunanda Gamage
38 posts
Sunanda Gamage
@gamage_sunanda
PhD candidate at Western University. Interpretable machine learning.
London, Ontario Katılım Temmuz 2019
5.1K Takip Edilen208 Takipçiler
@marksaroufim More visual elements (sketches, diagrams, etc) in the docs for "vaguely-named" functions like torch.tile, torch.repeat_interleave, etc that show how the input tensor is being copied/repeated/reindexed and how the `dim` param affects these functions' outputs!
eg for torch.roll:
English
If you could change one thing about PyTorch what would it be?
English
Sunanda Gamage retweetledi
Have you ever wanted to train LLMs in pure C without 245MB of PyTorch and 107MB of cPython? No? Well now you can! With llm.c:
github.com/karpathy/llm.c
To start, implements GPT-2 training on CPU/fp32 in only ~1,000 lines of clean code. It compiles and runs instantly, and exactly matches the PyTorch reference implementation.
I chose GPT-2 to start because it is the grand-daddy of LLMs, the first time the LLM stack was put together in a recognizably modern form, and with model weights available.
English
Sunanda Gamage retweetledi
Our preprint on OpenFold, our trainable reproduction of AlphaFold2, is finally up (biorxiv.org/cgi/content/sh…)! Since we open-sourced parameters in June, we've trained the model to high accuracy more than 50 times, on a variety of datasets. Here's what we learned (a lot) -> (1/19)
English
A treasure trove for software engineers.
🔎Julia Evans🔍@b0rk
it's the end of the year and some people have education budgets to spend. What tech books have really helped you?
English
@visakanv Somehow, the self-hatred was never there when I was a child. I think the hyper competitive world that you step into & the expectations that pile up on you as you grow up has a lot to do with this.
English
took me years to begin to understand that one of the most heroic things you can do is not hate yourself
English
@nickcammarata And if that's the case, we can think of Pali as the language of enlightenment. Maybe a few other adjacent languages too. Attaching a language to enlightenment can be a bad idea though.
English
@nickcammarata Do you feel that there are good/ direct English translations for these Pali words? I personally feel that these Pali words are loaded with context and refer to very specific states of mind (and other things) that don't translate very well to English or other languages.
English
It's great to see this kind of top notch work in the natural sciences being fully open source. I hope this becomes the norm.
Demis Hassabis@demishassabis
Last year we presented #AlphaFold v2 which predicts 3D structures of proteins down to atomic accuracy. Today we’re proud to share the methods in @Nature w/open source code. Excited to see the research this enables. More very soon! bit.ly/alphafoldmetho… bit.ly/alphafoldgithub
English
Sunanda Gamage retweetledi
applied-ml curated papers, articles, and blogs on data science & machine learning in production.
@eugeneyan
github.com/eugeneyan/appl…
English
Thankful for the appreciation and recognition! I had a bit of time to check on the legendary figures who have been the Honourable Mention Recipient each year in the past, and I am so honoured to join the club!
English
Sunanda Gamage retweetledi
If you have less than 3 hours to spare & want to learn (almost) everything about state-of-the-art explainable ML, this thread is for you! Below, I am sharing info about 4 of our recent tutorials on explainability presented at NeurIPS, AAAI, FAccT, and CHIL conferences. [1/n]
English
Sunanda Gamage retweetledi
With EigenGame, our team formulated PCA as a competitive multi-agent game, testing a new approach to an old problem. @iclr_conf they shared new insights & algorithms that scale to massive data sets & offer an alternative to explore fundamental ML problems: dpmd.ai/EG
English
Sunanda Gamage retweetledi
Sunanda Gamage retweetledi
If you’ve been fortunate enough to do well this year, consider joining me and @VitalikButerin by donating at the addresses below.
But if all you have is Twitter, help spread the word. For every RT, I’ll donate another $50 to fight COVID in India, up to $100k. #cryptovscovid
Sandeep | CEO, Polygon Foundation (※,※)@sandeepnailwal
With the efforts of @balajis we are trying to increase the reach of this fund Eth Address to donate: 0x68A99f89E475a078645f4BAC491360aFe255Dff1 BTC : bc1q220k2449fau0pxu9hfn28q3w4k99ep9hwsa5fa DOGE : D6fWVp613N3dyLM6Zoghj3dZaEjbGZ8gpX Tron : TSZMcrQzMLdKrgiMPoe2uQMHLeEpkf2j8E
English
Sunanda Gamage retweetledi
Are you an undergraduate student in Sri Lanka interested in pursuing graduate studies abroad? @goasksef is offering a 6-month mentorship program with individuals in STEM from all around the world 🌎 ‼️Deadline March 14! ‼️
SEF@goasksef
Join the ScholarX batch of 2021! Apply now! ScholarX is a 6-month program for Sri-Lankan undergraduates who would like to get free premium mentoring during their study period.
English
A great thread on differences between scientific fields and why there is no one scientific method.
Dr Kareem Carr@kareem_carr
I've worked in a lot of different sciences and what I've discovered is that each science is its own slightly bizarre alternate reality where the scientific method turned out differently.
English
@KayeEllen17 London, Ontario CA. And also Colombo, Sri Lanka. I am so sorry for your loss, and I wish her soul peace.
English
#TEAMMOLLY , please tell us where in the world you are located. We want to see how many people across the globe were touched by our extraordinary girl. We are going to mark them on a map to hang in our house, so that you all are always with us. You’ve brought us such strength.
English
There are a lot of things we can learn from this pandemic about personal and public health, and I hope we carry them over to post pandemic life.
Sabreen /صبرىن@dakhterakhter
I’ll never forget doing compressions in a young child who was slowly dying from Influenza B, his heart being the last organ to fail. He made it (🤲🏽❤️), which speaks to his absolute tenacity. Look at flu deaths in kids this yr. It’s remarkable. 👀 I hope we can learn from this.
English
@iamtrask When you said "from a safety standpoint", what immediately came to mind was that narrow AI may be less vulnerable to attacks, more performant and robust (at the narrow task), easier to verify, more interpretable etc. than general AI.
English