Srishti Gureja @sGx_tweets
MLE | RL(HF) @AiEleuther x: NLP @Translation, @picampusschool | interests: LLM train & inf optimization, alignment, MoEs | PyTorch Contributor Awardee '23 github.com/srishti-git1110 PyTorch Forums Joined May 2021-
Tweets1K
-
Followers2K
-
Following179
-
Likes6K
With a single 24GB RTX 4090, is it possible to "pretrain" llama 7B from scratch? With a single batch size, this requires atleast 58GB VRAM! Join me in 1.5 hrs @ 2230 IST on the @CohereForAI discord where I discuss the latest GaLore paper that makes this possible on a 24GB GPU.
simplest way to understand "prediction=compression" is kolmogorov complexity. data is more predictable = low complexity data is less predictable = high complexity
the mathematical formalization of unsupervised learning in terms of distribution matching is one of the simplest yet one of the most exciting ideas to me. it goes: for two data x & y, find F s.t. D[F(x)] is similar to D[y] - that's why unsup learning must work, mathematically.
Thanks a lot @PyTorch @linuxfoundation! 🔥❤️ Great to have received this. Looking forward to contributing much more substantially down the line.
But fundamentally, the kinds of things that are okay in a chatbot vs an educational app for children vs a coding assistant are different. At @AiEleuther we don't make commercial products. We make algorithms that people can finetune, build off of, and deploy in their contexts.
GQA (and MQA) are impressively useful for faster transformer inference while maintaining performance, and all the while are very simple to understand. Join me in 2.5 hours (at 2230 IST) @forai_ml 's discord server for a detailed walkthrough of these two papers!
working through RoPE's math & realising it's nothing but revising my undegrad lin algebra (intuition & concept) was fun. btw, I'll be presenting today on extending the context of models using RoPE - 2230 IST @forai_ml. Paper: arxiv.org/abs/2306.15595
Sebastian Raschka @rasbt
267K Followers 906 Following Machine learning & AI researcher writing at https://t.co/A0tXWzG1p5. LLM research engineer @LightningAI. Previously stats professor at UW-Madison.Dan | Machine Learnin.. @DanKornas
53K Followers 503 Following 🤖 ML Engineer 🔬 AI Educator 💻 I help you build AI skills through project-based learning ➡️ https://t.co/lC2UKMtRjjCharly Wargnier @DataChaz
112K Followers 31K Following 🥑 DevRel @Streamlit @SnowflakeDB 🪶 𝕏 about #AI, #LLMs, #DataScience, #WebApps, #SEO 💕 My heart is open source 🌍 Nature Lover 👀 My views!Nick Singh | The Data.. @NickSinghTech
30K Followers 4K Following Author of Ace the Data Science Interview. Free Book Preview 👇 https://t.co/1izgOFy1Kt Founder of https://t.co/yyE4B5Ltpf (SQL Interview Prep) Ex-FacebookAntaripa Saha @doesdatmaksense
4K Followers 420 Following ML - SproutsAI | Prev @DataFacade @DailyhuntApp | NIT-A 22TuringPost @TheTuringPost
62K Followers 16K Following Newsletter exploring AI & ML - Weekly trends - LLM/FM insights - Unicorn spotlights - Global dynamics - History Led by @kseniase_ Elevate your AI game 👇🏼harpreet @DataScienceHarp
7K Followers 1K Following 🤖 Generative AI Hacker | 👨🏽💻 AI Engineer | 👷🏽♀️ Developer Advocate | Building🏗️-Shipping🚢-Sharing🚀Chris Albon @chrisalbon
86K Followers 2K Following Director of Machine Learning at the Wikimedia Foundation. We host Wikipedia.Manish Sharma 📊 - .. @lucifer_x007
3K Followers 2K Following Human Machine Learning Engineer - 2 @hello_parspec || Gen-AI and LLMs || Research @iiscbangalore || Athelete : AI-Tech Shares : Roast : Random1LittleCoder💻 @1littlecoder
12K Followers 1K Following AI, ML, Open Source at - https://t.co/EKsvaArRIkAlejandro Piad Morffi.. @alepiad
17K Followers 1K Following Democratizing knowledge one keystroke at a time. PhD in NLP, full-time professor, CS Department @UdeLaHabana. Co-founder @syalia_srl.Ramsri Goutham Golla @ramsri_goutham
11K Followers 3K Following Shares learnings from bootstrapping 2 AI SaaS Apps to $100k ARR with no employees: https://t.co/fU8yoiYVDc https://t.co/DTyILliHVm My NLP courses: https://t.co/MYUyOxGSkASanthosh Kumar @SanthoshKumarS_
23K Followers 164 Following Conscious Data Scientist | Jr MLE @OmdenaAI | Sharing My Journey through Tweets. DM for Collaboration 📩Ishan Dutta | AI @ishandutta0098
3K Followers 907 Following ML Engineer II (GenAI) @Adobe | 18k on LinkedIn | Open Source @LightningAI | Ambassador @JarvislabsAI | Content @lancedb | @Kaggle MasterDelip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Rylan Schaeffer @RylanSchaeffer
3K Followers 971 Following CS PhD student with @sanmikoyejo at @stai_research @StanfordAILabSarthak Madhamshettiw.. @Sarthak_pm
134 Followers 866 Following Expert Noob Specialist @codeforces || 4🌟 @codechef || Knight @leetcode || @amazon MLSS 2023 || ML, DL, NLP Enthusiast || IIITA'25Maddy @maxzasu
7 Followers 12 FollowingMatt 🇺🇦 @matdmiller
865 Followers 2K Following AI, Engineer, Developer, Traveler, Technologist, @fastdotai Fellow, @[email protected]Elanchezhian @ElanchezhianKR1
21 Followers 164 FollowingWilliam de Vazelhes @WilldVaz
465 Followers 4K Following PhD candidate at @MBZUAI optim. & ML (esp. iterative hard-thresholding & zeroth-order). Ex @Huawei, Ex @Inria, MSc. @Supelec '16.jiangmaiqi @jiangmaiqi1
3 Followers 198 FollowingTaqi Haider🇵🇰 @taqihaider9
222 Followers 2K Following ML,DL practitioner | Tweets about #DataScience | #MachineLearning |#python | #AI |#FitnessloverHarshit Juneja @harshhiittyy
326 Followers 4K Following Understanding people and instructing machines. Thoughts and tweets are not mine or my employer's or my neighbour's. Probably they are yours.Siva S K @thesivask
131 Followers 1K Following Developer - Python & Go 🚀 | AWS Certified Solutions Architect ☁️ | AI/ML & LLMs 🧠| Sharing my coding journey & AI insightsZeeshan @Zshan_ashraf
23 Followers 470 FollowingPiyush @CatAstro_Piyush
315 Followers 843 Following Physics Grad student| Computational Physics| Natural Language Processing| Hydrogen StorageNikhil Velpanur @nikhilv
2K Followers 4K Following Experimenting with things that don’t make sense yet.Ibrahim Ahmad @Ibrahim63433664
85 Followers 3K FollowingArjun Srivastava @arjunsriv
62 Followers 1K Following AI, reinforcement learning, distributed systems something new @Woven_ToyotaJP prev - discovery @bookmyshow, cs @IITIOfficialSandeep Sudarshan @flapdoodle_sand
78 Followers 799 FollowingBen Everman @beneverman
131 Followers 1K Following software engineer, machine teacher, serial learnerthakurrajanand @thakurrajanand
175 Followers 2K Following Head of Data - Alraedah Finance | past @SnorkelAI @DataRobot @AmericanExpressYesKaey 🥑 @santosh_sto
163 Followers 4K Following Software Engineer 👨💻ex-Citi Product Development 🎯 Graphics Designer 🖌️ DJ 🎧 Badminton 🏸 Choose Love💙 Gotta go to Mars🚀Keep up if you're walking!Snehil Saluja @mesnhl
595 Followers 951 Following Co-founder @OverlayyAI | Code, Math, Logic and Design | Studied at @IITKanpur & @CMSJaiJagatsathiyamurthy @sathiyamurthys
83 Followers 824 Followingjulia. web3 @julidziesinska
207 Followers 5K Following 🇵🇱🇬🇭| Crypto | NFT | DeFi | Growth | DM for Marketing Inquiries & Business | NFAKesku @yoimnotkesku
677 Followers 2K Following Hiya, call me Kes! | Discord: kesku | More at @notjustkesku | Moderator @ https://t.co/K2y5k6uILo | Studying Data Science and Machine LearningHari @Haripallikere1
74 Followers 181 FollowingKUSHANG UPADHYAY @KUSHANGUPA49895
2 Followers 49 Following Persuing https://t.co/skhctGKG46 From CIPET IPT-JAIPURRyan Boyle @_RyanBoyle_
1K Followers 5K Following Tech Enthusiast 👨🏼💻 Aspiring ML Engineer. Frequent Traveler 🌎 Based in Philly & LA, Soon → SF 🌉zqmath1994 @zqmath1994
7 Followers 64 FollowingArindam Majee @arimajee
60 Followers 1K Following SDE-I at Amazon India | Ex-RA at IAI, TCG CREST & ISI Kolkata | Talks on GNN, Multimodal Learning.Arif Ahmad @arif_ahmad_py
254 Followers 7K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIKiran Raj Samarthyam @srkiranraj
210 Followers 2K Following agnostic, knowledge seeker, story teller, coder and wanna be entrepreneur...Vi @AvimanyuRoy3
578 Followers 2K Following 🍎🕊/🦦☕️/😴🛌/he/him Shouting into the Void (TM) GPU poor peasantSebastian Raschka @rasbt
267K Followers 906 Following Machine learning & AI researcher writing at https://t.co/A0tXWzG1p5. LLM research engineer @LightningAI. Previously stats professor at UW-Madison.elvis @omarsar0
189K Followers 486 Following Building with LLMs @dair_ai • Prev: Meta AI, Galactica LLM, PapersWithCode, Elastic, PhD • Creator of the Prompting Guide (~4M learners)Dan | Machine Learnin.. @DanKornas
53K Followers 503 Following 🤖 ML Engineer 🔬 AI Educator 💻 I help you build AI skills through project-based learning ➡️ https://t.co/lC2UKMtRjjCharly Wargnier @DataChaz
112K Followers 31K Following 🥑 DevRel @Streamlit @SnowflakeDB 🪶 𝕏 about #AI, #LLMs, #DataScience, #WebApps, #SEO 💕 My heart is open source 🌍 Nature Lover 👀 My views!PyTorch @PyTorch
379K Followers 77 Following Tensors and neural networks in Python with strong hardware acceleration. PyTorch is an open source project at the Linux Foundation. #PyTorchFoundationAntaripa Saha @doesdatmaksense
4K Followers 420 Following ML - SproutsAI | Prev @DataFacade @DailyhuntApp | NIT-A 22Alfredo Canziani @alfcnz
86K Followers 268 Following Musician, math lover, cook, dancer, 🏳️🌈, and an ass prof of Computer Science at New York Universityharpreet @DataScienceHarp
7K Followers 1K Following 🤖 Generative AI Hacker | 👨🏽💻 AI Engineer | 👷🏽♀️ Developer Advocate | Building🏗️-Shipping🚢-Sharing🚀Manish Sharma 📊 - .. @lucifer_x007
3K Followers 2K Following Human Machine Learning Engineer - 2 @hello_parspec || Gen-AI and LLMs || Research @iiscbangalore || Athelete : AI-Tech Shares : Roast : Random1LittleCoder💻 @1littlecoder
12K Followers 1K Following AI, ML, Open Source at - https://t.co/EKsvaArRIkAlejandro Piad Morffi.. @alepiad
17K Followers 1K Following Democratizing knowledge one keystroke at a time. PhD in NLP, full-time professor, CS Department @UdeLaHabana. Co-founder @syalia_srl.Ramsri Goutham Golla @ramsri_goutham
11K Followers 3K Following Shares learnings from bootstrapping 2 AI SaaS Apps to $100k ARR with no employees: https://t.co/fU8yoiYVDc https://t.co/DTyILliHVm My NLP courses: https://t.co/MYUyOxGSkAIshan Dutta | AI @ishandutta0098
3K Followers 907 Following ML Engineer II (GenAI) @Adobe | 18k on LinkedIn | Open Source @LightningAI | Ambassador @JarvislabsAI | Content @lancedb | @Kaggle MasterDelip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Quentin Anthony @QuentinAnthon15
1K Followers 126 Following I make models more efficient. Google Scholar: https://t.co/kzVsAKPdrpBrendan Dolan-Gavitt @moyix
25K Followers 6K Following Associate Professor @ NYU Tandon. Security, RE, ML. PGP https://t.co/3WXr0RfRkv Founder of the MESS Lab: https://t.co/zGycrX3Gmn "an orc smiling into the camera" — CLIPCosta Huang @vwxyzjn
3K Followers 1K Following RLHF @huggingface 🤗; main dev of @cleanrl_lib; CS PhD @DrexelUniv; Ex @CuraiHQ @weights_biases @NVIDIAAI @riotgames.Alex Havrilla @Dahoas1
1K Followers 503 Following Georgia Tech ML Researcher studying neural network learning theory and LLMs for mathematical reasoning. Intern at FAIR, MSFT Research. Co-founder of CarperAI.Keller Jordan @kellerjordan0
1K Followers 197 Following Independent research Prev MLE @ Hive AI, math @ UCSDAniket Singh @hymnjack_
181 Followers 548 Following AI this & AI that @writesonic, at the gym on most days, enjoy making videos on the internetSeungone Kim @seungonekim
925 Followers 832 Following Incoming Ph.D. student @LTIatCMU, M.S. student @kaist_ai working on LLM Evaluation & Systems that Improve with (Human) Feedback | Prev: @yonsei_u @NAVER_AI_LabDavid Hall @dlwh
2K Followers 1K Following Research Engineering Lead at @StanfordCRFM . Previously co-founder at Semantic Machines ⟶ MSFT. Lead developer of Levanter, Breeze. he/him @[email protected]Lintang Sutawika @lintangsutawika
383 Followers 565 Following Incoming Ph.D. student @LTIatCMU. Researcher at @AIEleuther. Maintainer of LM-Eval Harness. Here for machine learning papers and discussion.Zhiqing Sun @EdwardSun0909
2K Followers 1K Following CS PhD @LTIatCMU working on scalable alignment. BS @PKU1898EleutherAI @AiEleuther
19K Followers 76 Following A non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence. Creators of GPT-J, GPT-NeoX, and VQGAN-CLIPLouis Castricato @lcastricato
3K Followers 477 Following Math @uwaterloo, RLHF @BrownCSDept, Goosefluencer. x-RS @aieleuther, x-Head of LLMs @stabilityai, x-lead @CarperAI. co-founder @synth_labs. We're hiring.∞ Juan Carlos @jcponcemath
7K Followers 973 Following Sharing the beauty of maths ꩜ Always learning + maths applets + online books https://t.co/5H1X2ef6Gu ∞ 🙏 https://t.co/6vXMHuxiqa ❤️Fern @hi_tysam
2K Followers 199 Following I make tiny, speedy neural networks and community-funded open source research. I also do consulting! Often holds the CIFAR10 speed record ( ;) ). she/they ❤️:')Harsha @Sree_Harsha_N
197 Followers 466 Following MSc VisCom @Saar_Uni | RA @cispa | prev MIT Media Lab. Working on theory and systems for efficient deep learning.Daniel Han @danielhanchen
7K Followers 935 Following Building @UnslothAI. Finetune LLMs 30x faster https://t.co/aRyAAgKOR7. Prev ML at NVIDIA. Hyperlearn used by NASA. I like maths, making code go fastAndreas Köpf @neurosp1ke
5K Followers 453 Following Exploring ways to algorithmically model our world.XR-5 🐀 @xariusrke
819 Followers 250 Following High school dropout. Scaling neural networks to massive scale @huggingface. DMs open.Teknium (e/λ) @Teknium1
29K Followers 3K Following Cofounder @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE Support me on Github SponsorsAnshuman @anshuizme
898 Followers 270 Following Machine Learning Engineer @_FlipAI; @GoogleDevExpert in ML; prev: GSoC'23 Keras3 @Tensorflow; Technical writer @weights_biases; KerasNLP collaborator;Ashwarya Maratha @AshwaryaMaratha
289 Followers 292 Following Upcoming Intern @ https://t.co/HngTQ54izb , Research @Macquarie_Unithebes @voooooogel
4K Followers 519 Following ꙮ programming & LLM & SFF enjoyer @ https://t.co/aykxqKippW ꙮ games @ https://t.co/3Pz19vHOwd ꙮ 💞💍📝 @holotopian ꙮ she/they 🏳️⚧️Abhinav Upadhyay @abhi9u
10K Followers 2K Following Passionate Programmer - writes about AI, Python, Compilers, Systems Programming, Unix. Subscribe to my newsletter at https://t.co/ymkZXjD6V8Tri Dao @tri_dao
18K Followers 364 Following Incoming Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.Samanyou Garg @SamanyouGarg
3K Followers 51 Following Tweets and threads about AI, startups, and digital marketing. Founder & CEO @Writesonic and @TLDRThis 🚀Eric Zhang @ekzhang1
9K Followers 335 Following I think about systems and interaction design. Currently working at Modal. recently: reading group, furniture, photos, biking, dataviz, wandering the cityNiko Matsakis @nikomatsakis
14K Followers 464 Following Weird Al meets Grace Hopper. Rustacean. He/him. I work for @AWSCloud. Opinions on twitter and elsewhere are my own.Hyung Won Chung @hwchung27
18K Followers 229 Following Research Scientist @OpenAI. Past: @Google Brain / PhD @MITJames Lin @jlinbio
3K Followers 553 Following Slaying dragons. "Those who lack the courage will always find a philosophy to justify it." — Camus.Rylan Schaeffer @RylanSchaeffer
3K Followers 971 Following CS PhD student with @sanmikoyejo at @stai_research @StanfordAILabMark Simithraaratchy @marksimi
414 Followers 591 Following MLE & CompSci grad student @GaTech. Meta alum (DS mgmt). Here to encourage growth in both people and systems.Jack Rae @drjwrae
9K Followers 353 Following Principal Scientist @ Google DeepMind Work on Gemini 💎♊ Compression is all you need LLMs (e.g. Gopher, Chinchilla, Gemini) 💼 Past: OpenAI, QuoraEric Steinberger @EricSteinb
7K Followers 478 Following Writing code that writes code on a mission to build safe superintelligence | CEO/cofounder @magicailabsStella Biderman @BlancheMinerva
15K Followers 748 Following Open source LLMs and interpretability research at @BoozAllen and @AiEleuther. My employers disown my tweets. She/herAflah 🍉🕊️ @Aflah02101
181 Followers 982 Following Researching @mpi_sws_, @lcs2lab & @AiEleuther • Prev @GoldmanSachs • GSoC @TensorFlow • Senior @IIITDelhi • #CEASEFIRENOW 🕊️emozilla @theemozilla
4K Followers 1K Following catholic, ai research and co-founder at @NousResearch alignment: whatever the opposite of yudkowsky isThomas Steinke @shortstein
9K Followers 454 Following Computer scientist interested in (differential) privacy & related topics, e.g., generalization. @GoogleDeepMind Opinions are mine ©. 🇳🇿Yi Tay @YiTayML
29K Followers 97 Following chief scientist / cofounder @RekaAILabs 🫠 past: research scientist @google brain 🤯 currently learning to be a dad 🍼Trenton Bricken @TrentonBricken
6K Followers 2K Following Trying to figure out what makes minds and machines go "Beep Bop!" @AnthropicAIVilém Zouhar @zouharvi
2K Followers 2K Following PhD student @ ETH Zürich | all aspects of #NLProc but mostly HCI, evaluation and MT | go #veganBlinkDL @BlinkDL_AI
7K Followers 90 Following RWKV = 100% RNN with GPT-level performance. https://t.co/TkdxOJSFWX and https://t.co/86DzS6arA0william @wgussml
4K Followers 439 Following prev CMU PhD, OpenAI research scientist, helped build copilot & MineRL. working on a new startup. https://t.co/kz3WdDeyfyBerivan Isik @BerivanISIK
3K Followers 2K Following PhD @StanfordAILab. Scalable & trustworthy ML, transfer learning, language models, federated learning, privacy | prev: @Google @AWSCloud @VectorInstStill can't believe it's been 2 years since @CohereForAI :D. It's been an amazing experience interacting with the community, building a community project and the invaluable support of the C4AI team and @sarahookr for open source. Can't wait for what will come ^^
@danielhanchen You're the best. Keep up the great work 💪
@andrew_n_carr Oh we did get offers, but my bro and I want to try build a startup and help the OSS community! :)
not true, especially for language. if you trained a large & deep MLP language model with no self-attention, no matter how much data you'll feed it you'll still be lacking behind a transformer (with much less data). will it get to the same point? i don't think so. your tokens…
The dataset is everything. Great read: nonint.com/2023/06/10/the…
@tamaybes but current models don’t allocate parameters to rotary embs! this means the Chinchilla D=20*N is skewed already for the actual param counts of most models, even if it held across datasets! If we disregarded the pos. encoding params the coefficients would change
@tamaybes a super-fun arcane historical detail: Gopher (and by extension Chinchilla) use Transformer-XL style position encodings. This means they spend 20B params (Gopher) and 5B params (Chinchilla) on just rel. position encoding!
Fine-tuning turns generic pretrained language models into specialists. But how? In their #ICLR2024 work, researchers from @MIT_CSAIL, @KhouryCollege, and @TechnionLive reveal it's not about introducing new capabilities, but rather enhancing the existing ones!…
@sid_devic The only work I’ve come across on one-training-run + DP is the Steinke et al. work at Neurips’23 (arxiv.org/abs/2305.08846) It won an outstanding paper award too^^ (I’m sure you’ve come across this already)
An essential blocker to training LLMs on public domain books is not knowing which books are in the public domain. We're working on it, but it's slow and costly... if you're interested in providing support reach out!
@BlancheMinerva @rom1504 Indeed, these would be *extremely* valuable data resources. The databases on copyright.gov are, unfortunately, ununified and the records themselves seem anemic. Somewhat odd considering USPTO has flagship datasets (available via NAIRR). Greater financial incentives?
Consider being a labeler for an LLM. The prompt is “give me a random number between 1 and 10”. What SFT & RM labels do you contribute? What does this do the network when trained on? In subtle way this problem is present in every prompt that does not have a single unique answer.
One problem with finding ML talent since the bitter lesson is that ML is now distributed systems and statistics and our university system wasn't setup to produce people who are good at both.
Wouldn't say it's the most conclusive paper, but more findings in the direction we've been hearing: PPO can reliably edge out DPO performance. arxiv.org/abs/2404.10719 Quoting the abstract: "Experiment results demonstrate that PPO is able to surpass other alignment methods in…
The Encoder(-Decoder) lobby claims a long-awaited comeback with this release. (credit goes to @slippylolo for this masterpiece and @antoine_chaffin for reminding me of its existence)
Meet Reka Core, our best and most capable multimodal language model yet. 🔮 It’s been a busy few months training this model and we are glad to finally ship it! 💪 Core has a lot of capabilities, and one of them is understanding video --- let’s see what Core thinks of the 3 body…
I always assumed language is harder than vision since it evolved later. Even simple species have vision that allows survival. Thus, I thought we’d solve the “vision problem” before higher-level reasoning. That language is helping us solve the vision problem has been a surprise.
Silly things like "Split your DPO dataset up and train each part seperately" causing big gains is just.. typical lmao
Torchtune is shipping with LM Evaluation Harness integration for evals of finetunes! Excited to see lm-eval adopted by the ecosystem—evals are crucial. we (@lintangsutawika and I) are looking forward to collaborating with the torchtune team to build out deeper integration!
Really excited to officially release torchtune: a PyTorch-native library for easily fine-tuning LLMs! Code: github.com/pytorch/torcht… Blog: pytorch.org/blog/torchtune… Tutorials: pytorch.org/torchtune/stab… [1/5]
@Yampeleg You've said you want to promote high quality work outside of the big tech companies. Erasing the contributions of people outside of those companies does substantial harm to such people and is the exact opposite of promoting their work.
@Yampeleg Rotary embeddings became popular because of EleutherAI's models, not because of LLaMA. The LLaMA paper explicitly cites us as their inspiration, as do multiple papers that used the positional embedding before LLaMA did.
and now: Niloofar Mireshghallah on "What is differential privacy? And what is it not?" Why the focus on DP? Well, it appears many, many times in the EO! So let's talk about what this actually means. #genlaw