biswaboop⚡ @biswaroop08
creating stuff, @premai_io github.com/biswaroop1547 anywhere Joined January 2017-
Tweets684
-
Followers266
-
Following2K
-
Likes3K
We just integrated Prem's SDK with @LangChainAI and @llama_index. Now you can access all the current best LLMs and embedding models from @OpenAI @MistralAI @DbrxMosaicAI @AnthropicAI @AIatMeta etc and integrate them seamlessly with your existing LangChain or llama-index…
Time to test @metaai Llama 3. Two models have been released so far: - Llama3-70B-Instruct - Llama3-8B-Instruct ✅ Create an endpoint with Django Rest Framework. ❌ What port has 5 pins on the top and 4 on the bottom? ✅ I'm making pancakes for breakfast. I added a cup of…
Well well, all my devops x LLM friends out there, I heard it is a pain to manage GPU resources, installations, dependencies issues while deploying your LLMs on K8s. With Prem Operator, all of those can be done with just few commands, check this out 👇 github.com/premAI-io/prem…
Well well, all my devops x LLM friends out there, I heard it is a pain to manage GPU resources, installations, dependencies issues while deploying your LLMs on K8s. With Prem Operator, all of those can be done with just few commands, check this out 👇 github.com/premAI-io/prem…
The future of NLP is exciting, and we're diving headfirst into the world of small language models 🌎 Can they compete with their larger counterparts? And do we really need a 70B LLM for summarization? Large Language Models with parameter sizes ranging from 7 to 180B+ come with…
excited to speak at the AI in Production conference by the amazing @mlopscommunity. join me on 15th feb at 12pm pst (16th feb, 1:30am ist) as I discuss vision pipelines in prod and how we serve them @premai_io register here 👇 home.mlops.community/public/events/…
Open-Source LLMs Are Far Safer Than Closed-Source LLMs While everyone agrees that we don't have AGI yet, a reasonable number of researchers believe that future versions of LLMs may become AGIs The crux of the argument that closed-source companies use is that it is dangerous to…
NVIDIA basically compressed 30 years of its corporate memory into 13B parameters. Our greatest creations add up to 24B tokens, including chip designs, internal codebases, and engineering logs like bug reports. Let that sink in. The model "ChipNeMo" is deployed internally, like a…
📘 The State of Open Source AI (2023 Edition) github: github.com/premAI-io/stat… comprehensive guide exploring everything from model evaluations to deployment Thanks @premai_io for open sourcing
Gonna give my first ever lightning ⚡ talk on the current scenario on LLM evaluation. Do join us on Nov 7th with @LightningAI. We also have other cool talks on Distributed training, understanding attention etc.. Check out more here 👇 meetup.com/bangalore-deep…
Open-source AI is taking over the world. Here is a free, open-source book that will help you keep pace with everything that's happening: State of Open Source AI Book - 2023 Edition This is a living book. Anyone can contribute to it. Here is what you can find inside: 1/2
NVIDIA released new drivers and a AUTO1111 extension for using TensorRT with SD 1.5 and SDXL github.com/NVIDIA/Stable-… Works like a charm! Conversion on a 4090 is ~2mins and support multiple resolutions, batch sizes and loras!!
There's been so much going on in AI + open-source the past year it's hard to keep up 💨 We want to shoutout the "State of Open Source AI" book 📗 from our friends at @premai_io - covers models/dbs/mlops/toolkits and way more. Make sure to check it out! book.premai.io/state-of-open-…
A single compiled source of truth for all AI's (and related) current state information you need without wasting any time. Worked on few parts of it, do check it out!
Lots of LLM papers now pointing to "higher quality data" matters significantly more than quantity of data (always has been the case???). Phi-1.5 clearly showing that this works with a much smaller dataset. Caveat is that the data comes from an already capable model (gpt3-5,gpt-4)
Speculative execution for LLMs is an excellent inference-time optimization. It hinges on the following unintuitive observation: forwarding an LLM on a single input token takes about as much time as forwarding an LLM on K input tokens in a batch (for larger K than you might…
Speculative execution for LLMs is an excellent inference-time optimization. It hinges on the following unintuitive observation: forwarding an LLM on a single input token takes about as much time as forwarding an LLM on K input tokens in a batch (for larger K than you might…
Junaid Rahim @junaidrahxm
466 Followers 1K Following 👨🏻💻 @AtlanHQ • tweeting nonsense mostly • passionate about databases, systems, tech, design and the futureUzair @uzaxirr
2K Followers 656 Following Engineering @CivoCloud • prev @hackerrank, @yougotfam, @mydukaanapp, @walldotapp • I convert Coffee into code ☕ • Backend Dev 🛠️Suraj🌻 @electron0zero
2K Followers 2K Following Maker | Working on Tempo @grafana, ex- @clarisights | https://t.co/EcERaHRwBd & https://t.co/UyfcpC71AR | 💮🌻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 : RandomKunal Bhadra @oikunalbhadra
314 Followers 146 Following tech & data. finding the line between stupid and braveSarah Clayborne @clayborne_36173
84 Followers 5K FollowingKleo Austin @AustinKleo56761
53 Followers 5K FollowingCassidy Blisset @BlissetCassid
65 Followers 5K FollowingSindy Mcginn @SinMcgi
41 Followers 5K FollowingGlory Robe @GloryRobe6260
60 Followers 5K FollowingCyndy Norse @CyndyNorse15231
72 Followers 5K FollowingLakeshia Fales @FaleLakes
35 Followers 5K FollowingNadine Rode @rode_nadin17857
90 Followers 5K FollowingOralee Perruzzi @OraleeP68795
72 Followers 5K FollowingEstelle Belle @estel_belle
48 Followers 5K FollowingNatasha Durisseau @NatasDurisse
34 Followers 5K FollowingErica Couper @CouperEric16233
94 Followers 5K FollowingNwahiri Chigozie Chri.. @NwahiriChristi3
156 Followers 1K Following I'm Nwahiri Chigozie, CEO of Gozieafrik Tech. Apologies for any intrusion. I specialize in web development, data analysis, cryptocurrency $ affiliate marketing.Aakash Gorai @_aakashkumar_
52 Followers 328 Following upcoming swe intern @jpmorgan , still grinding dsa😅but more inclined to devAshleigh Badia @BadAshlei
86 Followers 5K FollowingAjay Khatri Chhetri @amajaying
81 Followers 137 Following Designer X Developer | CSE Sophomore, KIITMelina Baillie @BailMelin
68 Followers 5K FollowingLayla Houghtelling @LaHoughtelli
83 Followers 5K FollowingElsie-mae Ibara @mae_ibara89510
105 Followers 5K FollowingSanaya Alawdi @SanAlawdi
53 Followers 5K FollowingWai Strotman @strot_w
38 Followers 5K FollowingIsla-rae Bena @BenaRae58283
48 Followers 5K FollowingMaurine Hauge @hau_mauri
35 Followers 5K FollowingAddyson Barczak @AddysonBar26780
70 Followers 5K FollowingNena Pynes @NenaPynes83242
50 Followers 5K FollowingAlexandra Oborne @alexan_obor
73 Followers 5K FollowingChloe @Chloe5916248801
1 Followers 574 Following Travel/Reading/Sports/Co-founder/Refuse PornographyTommaso Dezzi @TommiDezziB
52 Followers 102 FollowingOcie Ross @OcieRoss9913
33 Followers 5K FollowingDinesh Kumar @dineshkumar541
2 Followers 14 FollowingAmogh Bhai @JeSuisAmogh
18 Followers 217 Following Expert in the only artform not bound by the laws of physics.Rima Durdan @DurdanRim
32 Followers 5K Followingdusan sekulic @sekulic87
38 Followers 390 FollowingAamina Polin @pol_aami
50 Followers 5K FollowingWhitney Hirsbrunner @WHirsbrunn98928
45 Followers 5K FollowingTrudi Revelo @trudi50000
31 Followers 5K FollowingEbony Spannaus @spann_ebon
48 Followers 5K FollowingJunaid Rahim @junaidrahxm
466 Followers 1K Following 👨🏻💻 @AtlanHQ • tweeting nonsense mostly • passionate about databases, systems, tech, design and the futureUzair @uzaxirr
2K Followers 656 Following Engineering @CivoCloud • prev @hackerrank, @yougotfam, @mydukaanapp, @walldotapp • I convert Coffee into code ☕ • Backend Dev 🛠️Adyasha ✨ @Adyasha8105
11K Followers 919 Following Engineer @hackerrank, not a hacker | Code and words 🌸| Building https://t.co/s2aVuc37qY🎵 | Opinions are my own🙊Google India @GoogleIndia
1.5M Followers 53 Following Searching for ways to make small businesses 💼 and our coffee ☕ stronger. Building a safer internet for a billion Indians 🌐merve @mervenoyann
56K Followers 4K Following open-sourceress at @huggingface 🧙🏻♀️ proud mediterrenean 🍋 I do TL;DR on ML papers sometimes. RTs != endorsementsAK @_akhaliq
309K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxKelsey Hightower @kelseyhightower
237K Followers 40 Following Minimalist DMs are now closed. Just email me: [email protected]Arpit Bhayani @arpit_bhayani
50K Followers 743 Following Co-founder and CTO at @profile_fyi • ex-Staff Engineer @Google and ex-DoE @unacademy • building Arbok, @TheDiceDB, and @RevineLang a → b ≠ ~a → ~bHussein Nasser @hnasr
58K Followers 649 Following Backend Podcast https://t.co/Td6AkF08Dr YouTube https://t.co/FfDg8cnnNa writes on https://t.co/i5ZOqUzJEZ Postgres https://t.co/PcX2tDsaI4 Engineer @esriKunal Kushwaha @kunalstwt
221K Followers 3K Following Driving innovation, educating minds, and strengthening developer relations @CivoCloudKIIT - Kalinga Instit.. @KIITUniversity
36K Followers 27 Following We are celebrating 25 glorious years of #KIIT #KIITat25Suraj🌻 @electron0zero
2K Followers 2K Following Maker | Working on Tempo @grafana, ex- @clarisights | https://t.co/EcERaHRwBd & https://t.co/UyfcpC71AR | 💮🌻chansung @algo_diver
4K Followers 569 Following @GoogleDevExpert for ML and @googlecloud | @huggingface Fellow | MLOps | Software Engineering | Open Source LoverSahil Khan @sahilk
11K Followers 1K Following Food. Design. Startups. What's your stance on bhindi? Product and design at @last9io.Kunal Bhadra @oikunalbhadra
314 Followers 146 Following tech & data. finding the line between stupid and braveTalia Ringer 🟣 �.. @TaliaRinger
26K Followers 6K Following Professor, @plfmse, @IllinoisCS! Proof Automation. @SigplanM & CCF Founder. Israeli-American for peace, equality, & justice. They/היא, ND, bi. די לכיבושLelouch 👾 @lelouchdaily
2K Followers 179 Following Documenting my ML grind. Posting daily progress reports & resharing memes.Meshcapade @meshcapade
2K Followers 52 Following The digital human company. Foundation models & 3D generative models to bring digital humans to life: https://t.co/X0fdkUyZwQ Join us! https://t.co/TtgfbguGwTNeil Katz @neilkatz
2K Followers 2K Following Helping the world build TRUTHFUL AI apps at @eyelevelai and https://t.co/Yz3KZVfGuQ. 4X Emmy winner.Deemos Tech @DeemosTech
5K Followers 268 Following Pioneering 3D Generative AI: https://t.co/uHgZ0XFSTy ChatAvatar: Text/Image to production-ready 3D avatars.Akanksha @akankshanc
403 Followers 406 Following Engineer, Amateur Astronomer, in love with thinking and analyzing, prefer rationalism in the sense of beliefs, happy to be blessed with an altruistic soulHerumb Shandilya @krypticmouse
2K Followers 424 Following NLP Engineer @SixHQai | Working on ColBERT, DSPy @Stanford | Learning @forai_ml | Chill @CreworkHQ | Ex-ML @sosimplified @DRDO_IndiaAW @TrainedOnTest
795 Followers 444 Following Senior data scientist / ML Engineer @ a massive unnamed corporation | I enjoy building thingsTheAIGRID @TheAiGrid
2K Followers 239 Following 200,000+ Subscribers On Youtube. The Latest In Artificial Intelligence News,Research and Updates. https://t.co/00h8FGPPlZ https://t.co/rWybeaStSeBarry’s Gardening S.. @BaryRockHard4ai
2K Followers 49 Following I’m Barry and I love Gardening and ai, I’m “ hip “ for it as my grandkids say.Mira @_Mira___Mira_
4K Followers 1K Following 🍎GI 2025 | Future World Ruler | Founder of Mira/acc | AGI via Mira-cle Star(M*) algorithm | Mira Supremacy is inevitable | X-risks,S-risks,M-risks(Mira risks)Matt Shumer @mattshumer_
51K Followers 1K Following CEO @HyperWriteAI, @OthersideAI - I make AIs do the impossible.Nathan Odle @mov_axbx
3K Followers 333 Following Just acc. Preferably on gravel. Drive rally cars, love dogs. Looking for my 7x4090 AI server build writeup? Check my site below.Jim Keller @jimkxa
34K Followers 134 Following CEO @tenstorrent, Cofounder @atomic_semi @BayaSystems and FlexAI board member. Fan of 2x2 matrixes, books, refactoring and creative tensionshreya @shreyaaatha
474 Followers 556 Following writing everywhere except walls, can be funny, designing new ways to enable small wins. Loves cows.Cercli @cercliHQ
24 Followers 8 Followingyifei e/λ @yifever
3K Followers 1K Following ex-PHD CERN | femboy enjoyer | ??? in tokyo | python standusan sekulic @sekulic87
38 Followers 390 FollowingIvan Leo @ivanleomk
2K Followers 736 Following Professional GPT wrapper writer, I write longer tweets at https://t.co/02byZNKMa8Raiba AI @Raiba_AI
561 Followers 1 Following join us in the new world powered by simponomics. powered by @Katsu_LabsSakana AI @SakanaAILabs
19K Followers 0 Following We are a Tokyo-based R&D company on a quest to create a new kind of foundational AI model based on nature-inspired intelligence. https://t.co/1q07mb3TzEDebangshu Bhattacharj.. @debangshub_
11 Followers 17 Following 📈 Data Platform Engineer | 📷 Photographer by hobby | 🎵 I love listening to music.Aditya Dalmia @AdiDalmia
28 Followers 112 Following Pizza🍕 | Technology🧑🏻💻 Computers understanding human language is exciting, isn't it?TimDarcet @TimDarcet
2K Followers 543 Following PhD student, building big vision models @ INRIA & FAIR (Meta)Tomáš Daniš @tmdanis
617 Followers 358 Following Natural intelligence researching artificial intelligence. Tweets about AI, alignment, tech, language learning and anything else I find interestingShannon Sands @max_paperclips
4K Followers 3K Following Software developer & aspiring cognitive architect https://t.co/JAoBrqMLXN Proudly TESCREAL & shitpost/acc. 🇦🇺 prideKarel D’Oosterlinck @KarelDoostrlnck
2K Followers 593 Following Interpretable AI, RAG, Biomedical NLP. Intern @ContextualAI, PhD student @ugent, visitor @stanfordnlp. Instigator of hikes.Geronimo @Geronimo_AI
774 Followers 380 Following LLM enthusiast 🚀 failing fast, learning fast. sharing it all on X and MediumAndreas Köpf @neurosp1ke
5K Followers 453 Following Exploring ways to algorithmically model our world.Mark Tenenholtz @marktenenholtz
114K Followers 544 Following Head of AI @PredeloHQ. XGBoost peddler, transformer purveyor.Rohan @clusteredbytes
3K Followers 249 Following Professional AI Engineer. Sharing what I'm currently learning, mostly about AI, LLMs, RAG, building AI powered software, AI automation etc.IT IS DONE!! I CAN GO TO SLEEP! Here's the (rough) alpha release of anime.gf, a local & open source alternative to CharacterAI ^-^
We just integrated Prem's SDK with @LangChainAI and @llama_index. Now you can access all the current best LLMs and embedding models from @OpenAI @MistralAI @DbrxMosaicAI @AnthropicAI @AIatMeta etc and integrate them seamlessly with your existing LangChain or llama-index…
accidentally spammed 10k+ folks with a test email TWICE anyways, how is your monday going?
@GokuMohandas @llama_index Ohh yes, Ray is used extensively on Model training at Prem, the journey is documented here too blog.premai.io/slm-training/
I enjoyed spending quality time with a close-knit group of friends, Idk just felt happy seeing them. - All of them adopted a dog 🥹 - A few of them dedicated an entire night to help another friend prepare for a tech talk.🥹
In 2019 I spent 25 days travelling in Europe and spent INR 103,945 (excluding flights & visa) Cities I stayed in: Munich, Berlin, Fussen, Salzburg, Vienna, Budapest, Prague, Karlovy Vary A thread for #budget travellers :) 1/7
Maybe there are little flat spots along the way, but AI in 5 years will be ridiculously capable compared to AI today.
“CPU gets hit with an interrupt and wakes up with a new thread in a completely different address space This is an isekai”
Claude has a nice trick where you prefill the start of the assistant response, and it continues from there. Anyone know if Llama 3 can do the same thing?
Someone beside me at the cafe in Vietnam is working on a presentation titled : "Best Practices to Prevent Shopping Addiction". They walked in carrying 3 shopping bags. 🛍️🤨
𝗰𝗿𝘆𝗽𝘁𝗼𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆 𝗶𝘀 𝘁𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝗽𝘀𝘆𝗼𝗽 𝗶𝗻 𝗵𝘂𝗺𝗮𝗻 𝗵𝗶𝘀𝘁𝗼𝗿𝘆. and you are what 'they' refer to as the 'useful idiots'. they knew that people would eventually fear inflation and abandon fiat money, so they created an 'alternative' that would…
New models out in the Prem Platform. - @cohere Command-R Plus - @MistralAI Mixtral 8x22 Both can be compared to GPT-4 in terms of performance. Give them a Try!
Delivered my first international talk at GitOpsCon North America ✨😊 Your Boi finally did it! ✅ Thanks for everyone who helped me to get here 😊🙌🏻
Let's say you have a K8s cluster with GPU, then deploying an LLM with chat UI is only 2-3 commands (YMMV)
Well well, all my devops x LLM friends out there, I heard it is a pain to manage GPU resources, installations, dependencies issues while deploying your LLMs on K8s. With Prem Operator, all of those can be done with just few commands, check this out 👇 github.com/premAI-io/prem…
Let's say you have a K8s cluster with GPU, then deploying an LLM with chat UI is only 2-3 commands (YMMV)
I get so many DMs exactly about this! So here you go! Prem's blog covers everything you need to know to get started with and ace Lora! 🚀
🚀 Diving into the efficient universe of fine-tuning LLMs with Low-Rank Adaptation (LoRA) and its cutting-edge variants! 🌟 🔅 LoRA has transformed how we fine-tune massive language models for new tasks, slashing computational demands! 🔍 🧠 Explore LoRA+ for dynamic learning,…
Well it's super easy to say lot of things about language models and their behaviours all theoretically or based on some already done experiments. But we learn a lot more, when it is done all hands on. At Prem, we are super keen to understand about Small Language Models. This…
Don't manually copy and paste your LLM's code into separate files like a chump -- do it in one go with this simple little trick!
@elonmusk @XEng Same here. @premai_io account has been suspended for no reason.
Yes, Typeform is shit expensive, but that's because they've not upgraded at all. It's exactly the same single-scree interface that it was 10 years ago. Imagine if OpenAI and Typeform had a kid— Introducing Metaforms AI