Shreyansh Singh @shreyansh_26
Building Conversational AI systems at @TheLevelAI | ex-AI Research at @Mastercard, @SamsungResearch | Interests - NLP, AI Safety, ML Systems Engg. shreyansh26.github.io New Delhi, India Joined June 2014-
Tweets2K
-
Followers533
-
Following2K
-
Likes12K
The Chinchilla scaling paper by Hoffmann et al. has been highly influential in the language modeling community. We tried to replicate a key part of their work and discovered discrepancies. Here's what we found. (1/9)
This line of @PyTorch code fascinates me every time I come across it: y = x_backward + (x_forward - x_backward).detach() As @ThomasViehmann explained: "It get’s you x_forward in the forward, but the derivative will act as if you had x_backward"
@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!
LOVE how the Meta team went hard on explicitly describing the prompt template llama.meta.com/docs/model-car…
Great read. Thanks for writing this!
17-year-old Indian prodigy 🇮🇳 Gukesh D makes history as the youngest-ever player to win the #FIDECandidates! 🔥 📷 Michal Walusza
We have just released 🍷 FineWeb: 15 trillion tokens of high quality web data. We filtered and deduplicated all CommonCrawl between 2013 and 2024. Models trained on FineWeb outperform RefinedWeb, C4, DolmaV1.6, The Pile and SlimPajama!
2 new tiny Apache 2.0 reranker models just got released by @JinaAI_. Despite their small size/latency, they perform competitively on benchmarks, reportedly outperforming bge-reranker-base and mxbai-rerank-base on MTEB Retrieval. Models: huggingface.co/jinaai/jina-re… Details in 🧵
Llama 3 has been my focus since joining the Llama team last summer. Together, we've been tackling challenges across pre-training and human data, pre-training scaling, long context, post-training, and evaluations. It's been a rigorous yet thrilling journey: 🔹Our largest models…
We just released Mixtral-8x22B-v0.1 and Mixtral-8x22B-Instruct-v0.1: - Free to use under Apache 2.0 license - Outperforms all open models - Native function calling - Masters English, French, Italian, German and Spanish. - Seq_len = 64K mistral.ai/news/mixtral-8…
Our computer vision textbook is released! Foundations of Computer Vision with Antonio Torralba and Bill Freeman mitpress.mit.edu/9780262048972/… It’s been in the works for >10 years. Covers everything from linear filters and camera optics to diffusion models and radiance fields. 1/4
🚀 Introducing Pile-T5! 🔗 We (EleutherAI) are thrilled to open-source our latest T5 model trained on 2T tokens from the Pile using the Llama tokenizer. ✨ Featuring intermediate checkpoints and a significant boost in benchmark performance. Work done by @lintangsutawika, me…
Question: What was the game changing moment? Ruturaj said "That young wicket keeper hitting 3 sixes in the final over". [Smiles]
YC Batch W24 - What're the AI trends? 247 companies just presented at demo day, I looked at them all to see where AI is going My favorites at the end. Link to full list below Popular Categories: * Voice Agents (6): @marrlabs, @retellai, @OpenCall_AI, @usearini, @hemingway,…
BREAKING: Peter Higgs, the physicist who theorized the Higgs boson, has died at the age of 94.
8x22B 👀
Unsloth now supports fine-tuning of LLMs with 4x longer context windows! We managed to reduce memory usage by a further 30% at the cost of +1.9% extra time overhead. Read our blog: unsloth.ai/blog/long-cont…
MS Dhoni entry on the 'Hukum' song. 💥
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models Significantly improved finetuned perf by simply changing the initialization of LoRA's AB matrix from Gaussian/zero to principal components of W repo: github.com/GraphPKU/PiSSA abs:…
merve @mervenoyann
56K Followers 4K Following open-sourceress at @huggingface 🧙🏻♀️ proud mediterrenean 🍋 I do TL;DR on ML papers
Nathan Benaich @nathanbenaich
51K Followers 32K Following solo member of investment staff @airstreet, brewing ambition @airstreetcafe, next token predictor @airstreetpress
MIT CSAIL @MIT_CSAIL
298K Followers 22K Following MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL). Media Inquiries: [email protected]
rohan anil @_arohan_
12K Followers 2K Following Principal Engineer, @GoogleDeepMind Gemini. prev PaLM-2. Tinkering with optimization and distributed systems. opinions are my own.
Joe Mayo @JoeMayo
14K Followers 6K Following Building @generellem - #AI, #opensource, and #startups. Writing my own content.
ChetWickstrom @ChetWickst36888
8 Followers 725 Following
Jindong Gu @Jindong73504766
296 Followers 891 Following Senior Researcher @UniofOxford, Faculty Researcher @GoogleResearch, PhD @LMU_Muenchen #ResponsibleAI #AISafety #GenAI Homepage: https://t.co/YOSVO3jb6h
morsebits @m0rseb1ts
28 Followers 224 Following 🔗💡 MorseBits: Bridging the Future with Blockchain & AI 🚀 | Expert Developers Crafting Innovative Solutions |
Puneet Dhanuka @DhanukaPuneet
315 Followers 4K Following Software @ PhonePe👨💻 |Tech + Entrepreneur, cricket + badminton | Now Health + Fitness enthusiast + Travel | Pictian.
Aaditya ; @Aaditya26082004
534 Followers 7K Following CS'26 • Machine Learning • Open-Source • Web Dev. • Algorithms • Jai Shree Krishna 🦚🪈
zg6nrkekpn3fkx5 @n2lnfl8n07om
6 Followers 547 Following We first transfer USDT to you TRC20, you return 90% to BEP20, you get 10% , 2K per day Our co hv a large amt of USDT need to from TRC20 convert to BEP20 network
mann @punsbymann
106 Followers 349 Following ML @google | ms cs/ai @USC | geometric deep learning, language modelling, all things compute
Arjun Srivastava @arjunsriv
63 Followers 1K Following AI, reinforcement learning, distributed systems something new @Woven_ToyotaJP prev - discovery @bookmyshow, cs @IITIOfficial
Ayush Srivastava @ayushiyerji
23 Followers 734 Following
Bilal Onur Eskili @bilalonureskili
9 Followers 43 Following Ms @ METU | EEE @ Bilkent | NLP Researcher | Interested in Deep Learning & Quantum Computing
Martin Andrews @mdda123
604 Followers 1K Following AI Research / Founder @ Red Dragon AI. Co-organiser of Machine Learning Singapore MeetUp. @GoogleDevExpert (ML). Fixed Income quant in NYC during AI winter
Pratik Pranav @PratikPranav11
19 Followers 302 Following AI Engineer @ThirdAILab | CSE UG at @iitdelhi | LFC Fan
Nightfury @parab_mithun
44 Followers 574 Following
MANIKANTA PALLAPOTHU @pallapothu_17
20 Followers 32 Following
VitaWillard @pWwqrI5v088g8
7 Followers 496 Following
Jesse Silverberg @SilverbergJesse
90 Followers 410 Following
Aditya Raghuwanshi @adityarg_
25 Followers 258 Following Working as a ML Engineer. AI/ML enthusiast. IITK '21. Força Barça
Ashish Nagar @ashishnagar
509 Followers 453 Following Entrepreneur, Founder @TheLevelAI, Product #Alexa, Climate Policy Buff, #Stanfordgsb Alumni, #IITdelhi alumni, Indian.
Rishabh Jain @RishabhJain_r
16 Followers 155 Following Software Engineer || Independent Researcher, AI and ML || IIT RPR’23
Jasper @jasperdelandsh
59 Followers 301 Following Current Master student Data Science at TU Wien 🇦🇹 - am 🇧🇪 - lived in 🇫🇮 before Did BSc & MSc Bio-science engineering technology @UGent
𐂅 @esoteric_cowboy
0 Followers 3K Following esotericist conducting private personal research in good faith to expand my understanding of the universe. retweets & follows aren’t endorsement, seriously.
Prakash Ramakrishna @kashr
113 Followers 496 Following https://t.co/eLzKNsUVV3, https://t.co/7n0dfL9pwy, https://t.co/fJNXjWrJL5, https://t.co/IMJNPsh2fz
Jordan Lazzaro @jordan_lazzaro
14 Followers 829 Following
Ariel Brand @ArielBrand2
6 Followers 166 Following
Udit Saxena @saxenaudit
164 Followers 616 Following Amateur vintner, coder, photographer - aspiring polymath
Iftekhar Chowdhury @iftekhar_hc
8 Followers 302 Following
Jonas Eschmann @jonas_eschmann
119 Followers 507 Following PhD student @ NYU. Working on reinforcement learning for continuous control @rl_tools
Deeptej More @Deepu_learning
77 Followers 1K Following Artificial Intelligence @NorthwesternU | prev @iitbombay, @ISBedu | Computer Vision | Meta Learning | Self Supervision
Abhilasha Ravichander @lasha_nlp
3K Followers 2K Following Postdoc @allen_ai, working on Natural Language Processing (#NLProc) | PhD @SCSatCMU @LTIatCMU | Friend of @NLPWithFriends | @[email protected]
Richard @SelfSimulating
65 Followers 218 Following
Yiran Wang @nlp_yiran
133 Followers 1K Following Researcher @NICT_Publicity 0xDC687816 #NLProc #OpinionsAreMyOwn
__ @mahfspq
12 Followers 245 Following
Madhav Aggarwal @madhavaggar
46 Followers 594 Following Masters in CS @ Cornell University | Machine Learning and Computer Vision Researcher
Meher Shashwat Nigam @ShashwatNigam99
324 Followers 989 Following Master's CS @GeorgiaTech. Prev-Analyst at @GoldmanSachs. CS grad @iiit_hyderabad. Interested in computer vision and generative AI!
Srini @SriniN123
397 Followers 3K Following Love Sports and Technology. Forever in a pursuit to become a 100x engineer. ( a lot of my retweets are for me to read later)
Matthieu Thiboust @mthiboust
1K Followers 2K Following AI & Neuroscience enthusiast. Author of the free ebook 🧠+🤖 "Insights from the brain: the road towards Machine Intelligence" (2020).
sanny 🌸 @0xsanny
3K Followers 2K Following
Andrew Carr (e/🤸) @andrew_n_carr
15K Followers 3K Following science @getcartwheel AI writer @tldrnewsletter advisor @arcade_ai Past - Codegen @OpenAI, Brain @GoogleAI, world ranked Tetris player
Harnoor Dhingra @harnoordhingra
279 Followers 587 Following Artificial Intelligence @CarnegieMellon | Computer Science @BITSPilaniGoa
Jiminator @Jiminator31
37 Followers 871 Following CS Student at NYU | Aspiring Machine Learning Researcher / SWE | Esports Fan
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.
Yann LeCun @ylecun
712K Followers 719 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80Gx
Andrej Karpathy @karpathy
980K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥
abhishek @abhi1thakur
81K Followers 663 Following 🤗 I build AutoTrain @huggingface 👨🏽💻 World's First 4x Grand Master @kaggle 🎥 YouTube 100k+: https://t.co/BHnem8fTu5 ⭐ GitHub Star
François Chollet @fchollet
470K Followers 769 Following Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.
Santiago @svpino
353K Followers 444 Following I tell stories about technology and teach hard-core Machine Learning at https://t.co/iZifcK7n47. YouTube: https://t.co/pROi08OZYJ
Delip 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 🌈
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)
Mark Tenenholtz @marktenenholtz
115K Followers 546 Following Head of AI @PredeloHQ. XGBoost peddler, transformer purveyor.
LiveOverflow 🔴 @LiveOverflow
142K Followers 1K Following wannabe hacker... he/him 🌱 grow your hacking skills @hextreeio
Andrew Ng @AndrewYNg
1.0M Followers 913 Following Co-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
Kunal Shah @kunalb11
879K Followers 1K Following
AI at Meta @AIatMeta
533K Followers 255 Following Together with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.
typedfemale @typedfemale
23K Followers 478 Following a really exciting new account "have you ever though you might be like scott alexander? very smart, but can't do math" - anon
Rafi Ayub @theayubinator
44 Followers 57 Following LLM fine-tuning at @MetaAI and @PyTorch. Formerly Microsoft and Stanford.
ElevenLabs @elevenlabsio
65K Followers 11 Following Our mission is to make content universally accessible in any language and voice.
Hieu Pham @hyhieu226
2K Followers 41 Following Making GPUs go brrrr @augmentcode 🤖 Past: Research Scientist at Google Brain 🧠 IMO Silver Medalist 🥈 waiting for LLMs to beat me. Tweets are my own opinions.
Wing Lian (caseus) @winglian
9K Followers 2K Following @axolotl_ai OSS maintainer. Axolotl AI founder. AI/ML tinkerer. Building tools for everyone.
Johannes Hagemann @johannes_hage
2K Followers 2K Following co-founder @PrimeIntellect | prev Research Engineer, scaling LLMs @Aleph__Alpha | interested in building decentralized AI, longevity, techno-optimism
Consensus @ConsensusNLP
9K Followers 399 Following AI-powered, academic search. We use language models to surface expert answers from research papers. Create an account today: https://t.co/VTvqZU6W9F
Sharan Narang @sharan0909
2K Followers 254 Following LLMs and AI Research (Llama 2 & 3 lead) @Meta | ex @Google (PaLM lead, T5), ex @Baidu (Deep Speech 2, Sparse Neural Networks), ex @Nvidia
OpenAI Developers @OpenAIDevs
72K Followers 0 Following Official @OpenAI account for anyone building on our APIs. Join us in building the future of AI. We ❤️ developers!
Liquid AI @LiquidAI_
4K Followers 18 Following Building state-of-the-art general-purpose AI systems from first principles.
xAI @xai
996K Followers 36 Following
Piotr Padlewski @PiotrPadlewski
1K Followers 319 Following Chief Meme Officer @ https://t.co/CtBrcKmliI, ex-Google Deepmind/Brain Zurich
Zihao Ye @ye_combinator
830 Followers 454 Following
Unsloth AI @UnslothAI
3K Followers 255 Following Making AI & LLMs more accessible + faster for everyone! 🦥 Github: https://t.co/2kXqhhvLsb Discord: https://t.co/1Gmc1SDElj
Costa Huang @vwxyzjn
3K Followers 1K Following RLHF @huggingface 🤗; main dev of @cleanrl_lib; CS PhD @DrexelUniv; Ex @CuraiHQ @weights_biases @NVIDIAAI @riotgames.
swyx @swyx
91K Followers 3K Following Anti-ego ideas for anti-ergodic life. Founder, @smolmodels ▹ Listen: @latentspacepod ▹ Read: @coding_career ▹ Join: @aiDotengineer
vLLM @vllm_project
785 Followers 11 Following A high-throughput and memory-efficient inference and serving engine for LLMs
Cade Daniel 🇺🇸 @cdnamz
579 Followers 494 Following Working on LLM inference in vLLM. Passionate about systems performance
Tristan Hume @trishume
6K Followers 330 Following Performance optimization lead @AnthropicAI. Profiling, distributed systems, dev tools, interpretability. [email protected]
David 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]
Tom Blomfield @t_blom
48K Followers 837 Following Group Partner at @ycombinator Cofounded @gocardless and @monzo
Fireworks AI @FireworksAI_HQ
5K Followers 65 Following 🎆 Generative AI Platform built for developers
Dylan Patel @dylan522p
39K Followers 685 Following SemiAnalysis Boutique AI & Semiconductor Research and Consulting DMs are open for consulting, quotes, or to talk shop
yi 🦛 @agihippo
3K Followers 81 Following secondary account, hardcore fans only. friend of @agikoala the great researcher, main account: @yitayml warning: hot takes.
Exa (prev. Metaphor) @ExaAILabs
9K Followers 9 Following supercharge your LLM with the web's knowledge API → https://t.co/M5QuIA55d2 search engine → https://t.co/iqim6Mz5S3 discord → https://t.co/tzBhQZ0Jfc We're hiring | DM us!
Louis 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.
Dr Obbs @dr_obbs
20K Followers 831 Following Engineer, Tech Mgr, PhD Fluid Mech., Motorsport Tech, Co-host for @brakingbiaspod, ✝️, Proud husband and dad, 🇹🇷/🇺🇸 living in 🇬🇧, opinions & snark my own.
Arseny Kapoulkine �.. @zeuxcg
12K Followers 66 Following Available for advising and consulting. Previously: technical fellow at Roblox. pugixml, meshoptimizer, calm, volk, niagara, Luau. https://t.co/PTS70xW8NM
Prof. Anima Anandkuma.. @AnimaAnandkumar
25K Followers 2K Following Bren Professor @caltech, Fmr Sr Director of #AI research @nvidia, Fmr Principal Scientist @awscloud, AI+Science, PDE, Neural operators. Views my own.
Winnie Xu @winniethexu
2K Followers 457 Following Cookin' up LLM alignment at scale. Raised by @MetaAI @StanfordAILab @GoogleDeepmind. BS in CS/Math @UofT.
Daniel Han @danielhanchen
7K Followers 941 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 fast
Tolga Bilge @TolgaBilge_
2K Followers 571 Following Leader of https://t.co/IiJWWuiWhD & https://t.co/Ep1VpsILyj — @Superforecaster, @SamotsvetyF, @Swift_Centre, @INFERpub — Mathematics graduate of @UiB & @UnivofStAndrews
Pieter Abbeel @pabbeel
78K Followers 435 Following Diffusion Models; Large World Model; UniSim; TRPO; SAC; Ring Attention; MAML; HER; Domain Randomization; Decision Transformer; LLM as Zero-Shot Planners; RFM-1
Jacob Jackson @jbfja
6K Followers 665 Following @SupermavenAI, https://t.co/9CA1cdahOp, started @Tabnine, formerly researcher @OpenAI
Nora Belrose @norabelrose
8K Followers 124 Following Working toward a free and fair future powered by friendly AI. Head of interpretability research at @AiEleuther, but tweets are my own views, not Eleuther’s.
Rishabh Mehrotra @erishabh
2K Followers 621 Following Head of AI @sourcegraph || PhD in ML from UCL, London ex-{Sharechat, Spotify, Microsoft Research, Goldman Sachs, BITS Pilani}
Saining Xie @sainingxie
14K Followers 1K Following researcher in #deeplearning #computervision | assistant professor at @NYU_Courant @nyuniversity | previous: research scientist @metaai (FAIR) @UCSanDiego
Eric Steinberger @EricSteinb
7K Followers 478 Following Writing code that writes code on a mission to build safe superintelligence | CEO/cofounder @magicailabs
Tony Dinh 🎯 @tdinh_me
126K Followers 853 Following Indie hacker. 🧠 @TypingMindApp $33K/mo 🛠 @devutils_app $5.5K/mo 🪄 @blackmagic_so (Acquired, 2023) 📸 @XnapperHQ (Acquired, 2024)
Nikolay Savinov 🇺�.. @SavinovNikolay
1K Followers 0 Following Research Scientist at @GoogleDeepMind Work on LLM pre-training in Gemini ♊ 10M context length in Gemini 1.5 Pro 📈
Jascha Sohl-Dickstein @jaschasd
19K Followers 625 Following Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.
NAVER LABS Europe @naverlabseurope
4K Followers 201 Following Biggest AI industrial research organization in France. #AI, #robotics, #computervision, #machinelearning, #deeplearning, #NLProc, #UX
for all my 19 year old cs major followers it's time to learn chinese buddy
Does anyone know if both Triton>=2.3.0 and Torch>=2.3.0 works on pre Ampere GPUs (no bfloat16 support) anymore? Colab and Kaggle has Tesla T4s, which only supports float16, and not bfloat16. So Triton 2.3 seems to refuse to compile anything :(
Ladies and gentlemen, this is Nico Rosberg shortly after becoming world champion in 2016. Watch how Nico nearly had a breakdown because a teenager named Max Verstappen gave him intense battles in an inferior car during his debut year for Red Bull. Before Nico decided to retire,…
Turns out you can actually just run full 32k context on a single 3090 using vllm at higher precision (bf16). Just enable "fp8" cache dtype. This is for llama-3 8B
The entire Indo-Pacific in a frying pan
A hotter-than-usual May 2024 predicted for the entire Indo-Pacific Based on forecasts from global agencies via @WMO
Apart from MS's farewell, I now desperately want CSK and Ruturaj to win this season just for Ruturaj himself Win the Orange cap. Win the IPL trophy as captain in first ever season & make a mockery of this BCCI selection who didn't even bother to include you in Reserves
Had to give a talk to some CEOs. They knew way more about LLMs than me. Asked one of them how, he said "I check Chatbot Arena every morning" 😆 New OSGAI talk from Hao Zhang (@haozhangml ) on Chatbot Arena, seemingly the only eval anyone trusts. youtube.com/watch?v=7njmta…
Heads up to Accelerate/FSDP users - most likely you'd want to update to `main@accelerate` which has just merged a PR github.com/huggingface/ac… that makes FSDP converge at the same speed as Deepspeed - should you have loaded your model in half-precision and not fp32 while using AMP…
so there's a rumor going around that GPT-5 is secretly out in the wild so OpenAI can benchmark it...
Memory is now available to all ChatGPT Plus users. Using Memory is easy: just start a new chat and tell ChatGPT anything you’d like it to remember. Memory can be turned on or off in settings and is not currently available in Europe or Korea. Team, Enterprise, and GPTs to come.
Llama 3 degrades more than Llama 2 when quantized. Probably because Llama 3, trained on a record 15T tokens, captures extremely nuanced data relationships, utilizing even the minutest decimals in BF16 precision fully. Making it more sensitive to quantization degradation.…
Excited to share three ML/LLM systems from CMU Catalyst lab, all of which will be presented at #ASPLOS 24. They optimize different aspects of ML/LLM systems and are all open source. We will be at ASPLOS next week. Please reach out if you are interested. A thread for them (1/n).
If you don’t read docs, you too can write delightful code
Dhoni is happy. CSK is happy. Chepauk is happy. CSK making a bloody good comeback today.
MS Dhoni in IPL 2024: 37*(16), 1*(2), 1*(3), 20*(4), 28*(9), 4*(1), 5*(2). 7 innings, 7 not-outs: Thala for a reason. 😄👌
Why isn’t everyone talking about this??? Deepspeed devs literally just created a datatype FP6 with full tensor core support on the a100’s. (Since nvidia left us stranded with int4/8) It is SO smart just reading through the kernel, my god.
LLaMA-70b inferencing using only a single GPU and achieving 1.69x-2.65x higher normalized inference throughput than the FP16 baseline. with Six-bit quantization (FP6) 🔥 Deepspeed has just recently released this Paper and also integrated the FP6 quantization - "FP6-LLM:…
LLaMA-70b inferencing using only a single GPU and achieving 1.69x-2.65x higher normalized inference throughput than the FP16 baseline. with Six-bit quantization (FP6) 🔥 Deepspeed has just recently released this Paper and also integrated the FP6 quantization - "FP6-LLM:…
I partially agree, but HF's own strategy is based on centralizing absolutely everything in the open source space. Models, datasets, demos, leaderboards... Now even papers through a thin wrapper on top of arxiv. Isn't that also concentrating power?
Biggest safety risk of AI is concentration of power and I doubt this board will help fight it!
The best part in this video was when Kumar Sangakkara removed his cap when he saw the father of Dhruv Jurel. 👌 - Sanga, humble as ever....!!!
Trends for United States
You might like
