mor-gemma-transformer.streamlit.app
I implemented Google DeepMind's MoR on Gemma 270M. The standard transformer won by a landslide. 📊 Results: • Standard: 6.03 loss / 3.2GB VRAM • MoR: 23.23 loss / 13GB VRAM Why? MoR's power is scale-dependent. Its complexity backfires on smaller models.
we've been hard at work improving @cursor_ai Agent, allowing you to delegate more tasks and let it work alongside you
agent works just like a human developer, with access to your tools, codebase context, and the ability to take actions
here's what Agent can do ↓
DeepSeek R1 training explained from their paper
So DeepSeek R1 was released last week, and there is a lot of buzz around, righfully so because it is an opensourced (MIT licenced) llm which is said to perform as good as o1.
It is very cheap compared to o1 (usage and training…
Announcing The Stargate Project
The Stargate Project is a new company which intends to invest $500 billion over the next four years building new AI infrastructure for OpenAI in the United States. We will begin deploying $100 billion immediately. This infrastructure will secure…
After securing a position at a tier 2 company, I took some time to reflect and recharge. Now I'm ready to refocus on my studies and aim for a tier 1 job. Here are some pics from my time off—grateful for the break and excited for what's next!
#Bengaluru#rainalert#jobhunting
"Based on everything you know about me, create 5 questions to my future self"
Ask this question to gpt and you can reflect upon yourself.
You can also try:What do you know about me that I might not know about myself based on our previous interaction which I had till now?
#gpt4
Swarm by openai is a multiagent framework
> Educational repo to showcase agent patterns
> Not meant for production (Who is going to stop me)
> Lightweight ( and less coupling)
This repo is open sourced and a goldmine for anyone working with ai agents
github.com/openai/swarm
3 Followers 380 FollowingI have the trust in God that he has my back that he will help me and take care of me and my siblings and all who are in this situation 🙏🏿
2K Followers 6K FollowingAI-first debug assistant with context-aware fixes suggestions for your failing builds
Trust FlyCI Wingman to keep your workflows green!
196K Followers 6K Followingcanadian startup founder. prev eng @ x, stripe. yacine_kv on insta
i make my memes with https://t.co/pWRBfY8kn2 -
I write a subscriber only blog. Subscribe!
63.7M Followers 1K FollowingIt’s our job to #GoThere and tell the most difficult stories. For breaking news, follow @CNNBRK and download the CNN app ➡️ https://t.co/7PQD7o6fLw
7.9M Followers 13 FollowingBitcoin is an open source censorship-resistant peer-to-peer immutable network. Trackable digital gold. Don't trust; verify. Not your keys; not your coins.
2K Followers 126 FollowingSr Staff MLE @GoogleDeepMind on Gemini efficiency. Ex @meta, Grad @stanford, @IITHyderabad. 2013-24 in SF Bay. Karma Yoga. Definite optimism.
1.1M Followers 305 FollowingNYT Bestselling Author of The 5 Types of Wealth. Gave up a grand slam on ESPN in 2012 and still waiting for it to land. Order my book below 👇
282K Followers 13 FollowingThe worlds official source for memes.
Brought to you by https://t.co/oJ0BTSe4dL
https://t.co/4ELgvhaZuH
https://t.co/TdutYMJ35X
[email protected] for inquiries
28K Followers 989 FollowingShipped 14+ profitable products over the past 2 years.
Follow along so you can do it too.
🤖 https://t.co/WmDPZwSGqT
👇 +13 others
275K Followers 447 FollowingCo-Founder of ByteByteGo | Author of the bestselling book series: ‘System Design Interview’ | YouTube: https://t.co/9gPSJSrtPU
354K Followers 1K FollowingML/AI researcher & former stats professor turned LLM research engineer. Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW).