Rajesh K @_krr12

Sol III Joined March 2008

Tweets

512
Followers

35
Following

576
Likes

470

Jonathan Frankle @jefrankle

a year ago

Meet DBRX, a new sota open llm from @databricks. It's a 132B MoE with 36B active params trained from scratch on 12T tokens. It sets a new bar on all the standard benchmarks, and - as an MoE - inference is blazingly fast. Simply put, it's the model your data has been waiting for.

31 255 1K 962K 492

Download Image

Machine Learning Street Talk @MLStreetTalk

a year ago

Teaser clip of @PetarV_93 discussing next-gen neural network architectures - it's going to be an exciting future!

13 15 164 16K 70

Download Video

Petar Veličković @PetarV_93

a year ago

TacticAI has now been published in @NatureComms ⚽️ This was one of the most fun projects I've done @GoogleDeepMind---GNNs & GDL making meaningful tactical suggestions for corners, favoured by football experts 90% of the time (vs. the original execution)! nature.com/articles/s4146…

Google DeepMind @GoogleDeepMind

a year ago

118 593 3K 726K 1K

Download Gif

5 48 311 61K 59

Omar Sanseviero @osanseviero

2 years ago

Introducing: Zephyr Gemma! The community has struggled to do a good preference-tune of Gemma, so we built an open-source recipe and trained a model to help people get started. Model: huggingface.co/HuggingFaceH4/… Demo: huggingface.co/spaces/Hugging… Handbook: github.com/huggingface/al…

6 56 291 33K 178

Download Image

Ida Momennejad @criticalneuro

2 years ago

📢 📢 Delighted to share our paper with the amazing team Safoora Yousefi, Leo Betthauser, @grockious @raphaelmilliere on neuro-inspired analysis of LLMs. Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in LLMs arxiv.org/abs/2310.00313 🧵1/n #Llama

5 30 169 21K 100

Download Image

Sebastian Raschka @rasbt

2 years ago

While everyone is talking about Sora, there's a potential successor to LoRA (low-rank adaptation) called DoRA. Here's a closer look at the "DoRA: Weight-Decomposed Low-Rank Adaptation" paper: arxiv.org/abs/2402.09353 LoRA is probably the most widely used parameter-efficient…

34 380 2K 228K 1K

Download Image

Rajesh K @_krr12

2 years ago

I just published Demystifying LangChain Expression Language link.medium.com/i188DHcqJFb

0 0 0 11 0

Rajesh K @_krr12

2 years ago

I just published Retrieval-Augmented Generation (RAG) using Llama 2,ChromaDB , Together AI for Retrieval QA link.medium.com/nCipsppy3Eb

1 0 1 60 0

AdapterHub @AdapterHub

2 years ago

🎉 Exciting news! The new Adapters library for modular and parameter-efficient transfer learning is out! 🤖 Now simplified & disentangled from @huggingface pip install adapters pip install transformers 📄arxiv.org/abs/2311.11077 👾 github.com/adapter-hub/ad… #EMNLP2023 🧵👇

7 102 464 123K 271

Download Image

AI at Meta @AIatMeta

2 years ago

Today we're sharing new research that brings us one step closer to real-time decoding of image perception from brain activity. Using MEG, this AI system can decode the unfolding of visual representations in the brain with an unprecedented temporal resolution. More details ⬇️

62 477 2K 588K 609

Rajesh K @_krr12

2 years ago

forbes.com/sites/robtoews…

0 0 0 17 0

Rajesh K @_krr12

2 years ago

I just published Survey on Anomaly Detection using GNN’s— Part 1 link.medium.com/44wTITzxfCb

0 0 0 35 0

Rajesh K @_krr12

2 years ago

0 0 0 28 0

Download Image

MIT Mathematics @MITMath

2 years ago

Prof. Gil Strang's last lecture is ... Monday! Watch it via live stream: grinfeld.org/strang/

215 2K 10K 2.0M 1K

Download Image

AI at Meta @AIatMeta

2 years ago

Introducing ImageBind by Meta AI: the first AI model capable of binding data from six modalities at once. This breakthrough brings machines one step closer to the human ability to bind together information from many different senses. More on this new open source work ⬇️

53 416 2K 333K 341

Rajesh K @_krr12

3 years ago

Do you remember when you joined Twitter? I do! #MyTwitterAnniversary

0 0 0 36 0

Download Image

Quanta Magazine @QuantaMagazine

3 years ago

Machines can already translate one natural language into another, such as from French to English. Translating informal mathematics into computer code is a harder challenge, but researchers recently made progress. quantamagazine.org/to-teach-compu…

0 27 94 21K 20

OpenAI @OpenAI

3 years ago

We’re developing a new tool to help distinguish between AI-written and human-written text. We’re releasing an initial version to collect feedback and hope to share improved methods in the future. openai.com/blog/new-ai-cl…

655 2K 9K 3.2M 757

Andrej Karpathy @karpathy

3 years ago

🔥 New (1h56m) video lecture: "Let's build GPT: from scratch, in code, spelled out." youtube.com/watch?v=kCc8Fm… We build and train a Transformer following the "Attention Is All You Need" paper in the language modeling setting and end up with the core of nanoGPT.

483 3K 20K 5.1M 9K

Download Image

AI at Meta @AIatMeta

3 years ago

Meta AI presents CICERO — the first AI to achieve human-level performance in Diplomacy, a strategy game which requires building trust, negotiating and cooperating with multiple players. Learn more about #CICERObyMetaAI: bit.ly/3GBwLzx