Asish Binu Mathew @kernelguardian

Inspired by @karpathy's nanoGPT, I've been building nanoPaLM🥳 A fast & lightweight repo for training small to medium sized PaLM models. So far I've trained a 213M model for 100k iters in 24hours on a single 3090, and that gets cut in half on a 4090! 🤗github.com/RobertRiachi/n…

7 78 459 69K 214

Download Gif

Asish Binu Mathew @kernelguardian

2 years ago

Sums up LLM space right now 😂

Avery Edison @aedison

2 years ago

Sums up LLM space right now 😂

127 5K 45K 4.3M 1K

0 0 0 348 0

Nazneen Rajani @nazneenrajani

3 years ago

I came to terms with the fact that I'd have to update the timeline ever so often, but I must admit that I did not think I'd have to update the model accesses so frequently. PaLM: closed --> limited Claude: closed --> limited

3 44 201 25K 66

Download Image

Asish Binu Mathew @kernelguardian

3 years ago

if you ever lose sight of why you started out in the first place, remember that its because you are stuck in a valley of local minima and the peak of global maxima is waiting for you 🌚

0 0 0 25 0

Download Gif

Keunwoo Choi @keunwoochoi

3 years ago

whoa, this is bigger than ChatGPT to me. google almost solved music generation, i'd say. google-research.github.io/seanet/musiclm…

129 1K 6K 1.2M 3K

Supabase @supabase

3 years ago

feeling cute... let's give away some Supa-swag. Like + RT for chance to win ⚡

94 565 902 119K 9

Download Image

ptrblck @ptrblck_de

3 years ago

@soumithchintala @kaikim29 Hahaha, the new design just dropped:

5 7 169 7K 1

Download Image

Thiago Ghisi @thiagoghisi

3 years ago

I've read thousands of articles over the last 20 years in Tech. Agile, Career, Distributed Systems, Engineering Management, Metrics, Programming, Testing, Types... Below are The 22 Articles that Impacted my Career the most ➕ my main highlights from each one. 🧵🧵🧵

52 306 2K 268K 3K

Jim Fan @DrJimFan

3 years ago

It's mindboggling that many years of research, engineering, community engagement, and meticulous benchmarking all distill into a single, elegant, plug-and-play function: torch.compile() You rarely get to see so much behind the scene in a single blog. pytorch.org/get-started/py…

3 155 1K 188K 400

Gergely Orosz @GergelyOrosz

3 years ago

I created a page titled “The Tech Resume Inside Out Free PDF”, where I offer a free PDF of the book, after explaining the work that went into it. The book is free - always will be - for any dev w/o a job. And I offer an early version for everyone else: thetechresume.com/free-pdf.html

7 6 165 28K 39

Download Image

Stephen Wolfram @stephen_wolfram

3 years ago

How does the impressively human-like #ChatGPT get computational knowledge superpowers? Give it a Wolfram|Alpha neural implant! writings.stephenwolfram.com/2023/01/wolfra…

96 873 4K 826K 956

Download Image

Theo - t3.gg @theo

3 years ago

What better time than now to release my React Bro's Guide to Frameworks 😅 link to video below

84 298 2K 327K 753

Download Image

Alex Xu @alexxubyte

3 years ago

1/2 Linux commands illustrated on one page! 🔹Controlling processes: kill, killall, nice 🔹Scheduliing jobs: sleep, watch, crontab 🔹Host location: host, whois, ping 🔹Many more Subscribe to our weekly newsletter to learn something new every week: bit.ly/3FEGliw

62 690 3K 302K 1K

Download Image

PyTorch @PyTorch

3 years ago

If you installed PyTorch-nightly on Linux between Dec. 25 and Dec. 30, uninstall it and torchtriton immediately and use the latest nightly binaries. Read the security advisory here: pytorch.org/blog/compromis…

15 501 762 523K 63

Download Image

Allistair McCaw @AllistairMcCaw

3 years ago

This is so heartwarming ❤️ Parents, teach your kid to have the character and compassion of the kid in blue 💙

9K 51K 480K 62.1M 7K

Download Video

Mark Tenenholtz @marktenenholtz

3 years ago

Someone implemented a framework to allow you to train PaLM (Google’s 540B parameter LM) using the same reinforcement learning strategy as ChatGPT! Open source strikes again. To start, here’s the part where you initially pre-train the model: