Abacus.AI @abacusai
Use Gen AI to build Applied AI agents and systems. AI builds Applied AI while DS teams supervise and evaluate the results. Working towards open-source AGI abacus.ai Joined April 2019-
Tweets2K
-
Followers49K
-
Following6
-
Likes872
FIRST EVER Long Context (128K) Llama-3 70B - Llama-3-Giraffe-70B From Abacus AI The biggest issue with the Llama-3 family is that they are fairly small context models. So, even though they are as performant as GPT-4 on critical benchmarks, they can't be used in the real world…
Increase your productivity by 50%! Our data science co-pilot can: •Analyze and clean your data •Create plots and visualize data •Train predictive models You can set up a RAG system or fine-tune your models easily
AI Agents Are Going To Be Ubiquitous, And You Can Build Them Using The English Language The simple way to build AI agents is to simply specify what you want in the english language and then let the AI do the planning, coding, and building Write a detailed 2-3 line prompt, and…
The "Office Suite of AI" Bindu Reddy @bindureddy is founder/CEO of Abacus AI, a company that makes a suite of tools that you can use to turn your business into an AI-run workhorse. Here she talks to business people who are starting to implement AI, or are interested in learning…
Unless you need a very specific type of output/task, fine-tuning is typically a bad idea. •LLM progress is very fast and there’s a new LLM released nearly every day. The chances that your fine-tuned LLM will be state of the art is very low. •RAG and extended context is a…
@bindureddy I've been playing with Llama 3 Smaug-8B all day on @private_llm. It's a solid Llama 3 finetune. Great job!
The Private LLM guys made Llama-3-Smaug from Abacus available on their iPhone app. It's a very good small model... and works pretty well on a mobile device. Who would have thunk it? - LLMs running on your phone 🤯🤯
LLMs are already pretty intelligent; they can distinguish between strong and weak arguments, predict stances based on beliefs and demographic characteristics, and determine the appeal of an argument to an individual based on their traits. The paper below shows that LLMs perform…
Create Complex Agents In Hours!! You can create a customer service agent and integrate it with your customer service software like Zendesk in hours... AI, not humans, build these agents on our platform
The average MT-Bench score of Llama3 is 8.04. The new model's score is 8.25. That's a large jump! And it only took a few days. The name of the model is Llama-3-Smaug-8B, and it was created by the team @abacusai. Here is the model in HuggingFace: huggingface.co/abacusai/Llama…
Our AI Agents vertical is our fastest-growing vertical. It can help you crank out multiple bots to perform different tasks of varying complexity. Some of our customers even want to make 700+ agents! You will need support for: •Dynamic RAG, information retrieval, and vector…
Building AI Agents - build agents to automate simple tasks - show ROI quickly - in the beginning, these agents will mostly be assistants to humans - agents that talk to internal systems, pull repeats, send emails and interface with you on slack / teams are the most popular -…
Please Stop Saying Open Source AI Makes No Money Takes claiming open-source AI and software are pointless because we live in a for-profit capitalist society make NO SENSE - Meta open-sourcing Llama is a strategic masterstroke and serves its business interests. The community…
MT-Bench Scores And Why They Matter? MT-Bench is an LLM benchmark that measures an LLM's ability to engage in coherent, informative, and engaging conversations. It is designed to evaluate the performance of LLMs in having conversations and following instructions - attributes…
🚨New GGUF alert! - 5x new high-quality IQ based quantized models for "Meta-Llama-3-70B-Instruct" by @AIatMeta - 10x new GGUF models for "Llama-3-Smaug-8B" by @abacusai Models are available on @huggingface (links are in the comments) - as always, thanks for the support ❤️
My conversation with the Wall Street Journal and the need for unbiased, liberated LLMs that don’t exercise thought control We at Abacus AI are working on several fine tunes in the space including agentic LLMs! Yes, they will be safe and no, they won’t have access to the…
Interesting topic @mims Anti-woke AIs and Agentic AI Nice to see @bindureddy and @abacusai introduce "Liberated Qwen" that will answer any question prioritizing it's learning first wsj.com/tech/ai/here-c… via @WSJ
Llama-3-Smaug-8B 🦙🐉 Finetuned from Meta-Llama-3-8B, build for improving performance on real world multi-turn conversations. via @abacusai @bindureddy @crwhite_ml @arvinds 👏 HuggingFace: huggingface.co/abacusai/Llama…
World's Best Small Model - Announcing Llama-3-Smaug-8b! - Significant MT-Bench improvement Imagine if a llama and a dragon had a baby! - We would have an altogether better model in the form of Llama-3-Smaug-8B!! The model is available on Hugging Face NOW and significantly…
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/pROi08OZYJKirk Borne @KirkDBorne
447K Followers 6K Following Advisor to startups. Freelancer. Global Speaker. Founder @LeadershipData. Top influencer in #BigData #DataScience #AI #IoT #ML #B2B. PhD Astrophysics @CaltechAkshay 🚀 @akshay_pachaar
136K Followers 418 Following Simplifying LLMs, MLOps, Python & Machine Learning for you! • AI Engineering @LightningAI • Lead DataScientist • BITS Pilani • 3 Patentselvis @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)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 #MOOCsCharly Wargnier @DataChaz
112K Followers 31K Following 🥑 Developer Advocate at @Streamlit 🪶 𝕏 about LLMs, AI, Data Science, Web Apps and SEO 💕 My heart is open source 🌍 Nature Lover 👀 My views!Shubham Saboo @Saboo_Shubham_
41K Followers 449 Following AI Products @tenstorrent 📕 Author of books on GPT-3 & Neural Search in Prod ✍️ Tweets about LLMs & Prompt Engineering 📩 DMs open for collabAfiz ⚡️ @itsafiz
33K Followers 448 Following Full Stack Engineer 👨💻 - Simplifying Python, Data Science, ML and LLMs ✨ - Open for Collaboration 📩Bindu Reddy @bindureddy
124K Followers 339 Following CEO of @abacusai, using Gen AI to build Applied AI and LLM agents and systems at scale, ex-AWS / Google, passionate about human behavior and open-source AGIMachine Learning FLX @machinelearnflx
164K Followers 30K Following Everything about #MachineLearning #NLP #DeepLearning #AI #GenAI #Bigdata #Analytics #DataMining, #DataScience #Courses #Learning #ArtificialintelligenceAI Pub @ai__pub
72K Followers 343 Following AI papers and AI research explained, for technical people. Get hired by the best AI companies: https://t.co/MySVjUGOQ3Sumanth @Sumanth_077
47K Followers 862 Following Simplifying the concepts of Python, LLMs, Machine Learning & Data Science! • ML Developer Advocate @clarifai • Data Scientist • Building with AILior⚡ @AlphaSignalAI
84K Followers 898 Following Covering the latest in AI R&D • ML Engineer • Ex-Mila researcher • MIT Lecturer • Building AlphaSignal, a technical newsletter read by 180,000+ ML experts.Aishwarya Nevrekar @nevrekaraishwa2
45K Followers 960 Following I post about data science and memes. Chapter Lead at Omdena Mumbai Chapter Your only limit is your mind. DM for Collaborations 📩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-FacebookKirsten Lum | CTO & L.. @machsci
10K Followers 622 Following 🌲🌲 Applied ML/AI, data science, MLOps | Wife of 1, mom of 2 | Co-Founder and CTO of https://t.co/67wk0TNMlO | Quote: Oliver Wendell Holmes 🕊️Chris Albon @chrisalbon
86K Followers 2K Following Director of Machine Learning at the Wikimedia Foundation. We host Wikipedia.KDnuggets @kdnuggets
219K Followers 376 Following Data Science • Machine Learning • AI • Analytics • Founded by Gregory Piatetsky-Shapiro • Edited by @mattmayo13 • KD stands for Knowledge DiscoveryDavid Miller 🧮 @thedavescience
11K Followers 275 Following Accountant → Data Scientist → SMB Owner Showing you how to use data and automation to grow your local business.Rohit Ghumare | That .. @ghumare64
57K Followers 754 Following 🥑 @cerbosdev @devrelasservice Ex @soloio_inc ☁️ @googledevexpert for @googlecloud 😶🌫️ #CloudNativeAmbassador by @cloudnativefdn 👨💻 https://t.co/rWVBHq2daZCanademica 🇨🇦�.. @canademica
382 Followers 123 Following Validated #PrivateSchool Listed by the Ministry of Education #Ontario #CANADA BSID#889251 #futureofwork #innovation #entrepreneurship #AI #AIethics #AIEdYxl @bazahai23
11 Followers 47 FollowingQuantum McKaronn 🇨.. @McKaronn
12 Followers 210 Following Artificial life engineer evolving masterpieces. Is 'I' a coding error? Weaving life line by line, fueled by coffee & doubts. Here to learn & overthink.Sanjay @SabhyaK
9 Followers 158 FollowingEvolaition @evolaition
17 Followers 27 Following Specialising in Business ↔️ AI Integration. Increase your profits and improve efficiencies! Creators of Custom Digital Art. Free consultation!Jahnavi @jahnavi_32
1 Followers 27 FollowingChoubi @95aChoubi
2 Followers 3 FollowingChandra Lindy @ChandraLindy
30 Followers 403 Following Full-stack developer, AI/ML enthusiast & solopreneurDax Allen @DaxEAllen
9 Followers 58 Following Got promoted to senior software engineer so I could generate chibi D&D kittens.Andrew George @andrewjoegeorge
316 Followers 462 Following Educator, part-time blogger. I used to make films for a living, along with other creative endeavours. From Treaty 3. (He/Him)Juanes @Juanshot_
111 Followers 1K Following made in Venezuela 🇻🇪 I have my sword and shield . A warriorshirokuma2 @shiroku2222
0 Followers 32 FollowingAndrew Yao @YaoYuanxin
61 Followers 139 Followingameya.wagh @ameya_wagh
163 Followers 128 Following Robotics & AI . Solving perception for autonomous vehicles.Vlad Frolov @vfrolov
181 Followers 870 Following Here for marketing and operations wisdom but easily distractedBen @bmwilentz
73 Followers 3K FollowingD Lanou @JustWatchin
5 Followers 183 FollowingDarnesh Narla @narladarnesh
34 Followers 168 FollowingAlishan Jadhavji @AlishanJadhavji
26 Followers 63 FollowingNadia Bakir @NadiaJBakir
189 Followers 1K Following 🇮🇪 🇸🇾 Co-Founder @pixelz__ai (Acquired)🎨 @crankcrm 👩🏼💻 @AIAvatars_ 🚀@fridaycollectiv Mummy, Wife, Crossfitter. Views are mine. 👧🏼👶🏼🐱Heather Wu @hwuMadroneHill
133 Followers 1K Following I have been on Twitter and X since 2007, but I just created this work account. I own an RIA firm in San Francisco: https://t.co/28btQoUBvVAshvin A Janardhan @ajash81
28 Followers 220 FollowingDaniel Arista @TrustInAutonomy
294 Followers 879 Following Founder working to preserve human rights and agency from the growing threat of non-consensual use of AI. 20 year tech veteran, military veteran, PhD in CogSci.Satistix @satistix
180 Followers 636 FollowingPaul Smith @paulcsmith
987 Followers 778 Following I like making software. Created @luckyframework. Working at @github.Ahmed Mekallach @Ahmekal
3K Followers 104 Following 🌐 Transforming Work with Generative AI Agents | 🔧 Mastering AI for a Simpler Life | ⏰️Reclaim Your Time | 💼 CEO @Mytegroupdavid herring @dave86rx7
80 Followers 260 Followinguday somayajula @udaysomayajula
14 Followers 49 FollowingR4h1mH @R4h1mH
1 Followers 70 FollowingKyle @kylesuffolk
263 Followers 826 FollowingJermaine jeffries @Jermainejeffri1
43 Followers 641 Following Educational and FinancialConsultant, Entrepreneur, Evangelist and Employment Agent .Hpremium @web3nam3
789 Followers 3K Following https://t.co/Tes5ZFnfVs • https://t.co/NuhiRgwvTP https://t.co/3H4X5XEq21 •https://t.co/oOCFfDThZ2 • https://t.co/wMpswOH3Xa • https://t.co/cW7uHNvbfy • https://t.co/VYahFk94rN •https://t.co/Gik8R81APV• https://t.co/Uvx07c8pI2 • https://t.co/yp6o2BXYZH•https://t.co/0V7mofFuIl •📈phylosS @seg_fault_50
1 Followers 58 Following‘zurdo’ @maudusae
135 Followers 1K Following Mexican northeastern metalhead undergraduate student. CompBiol, MachineLearning n' DataMining in Biology. I once synbio’ed. Box n’ Muay Thai.Akash @pocuseverything
2K Followers 5K FollowingSurya Pratap Singh @pratap_surya_
38 Followers 128 Following Passionate about Statistics, Machine Learning & AI | MS in Machine Learning & AI from @LJMU | Sharing insights and discoveries in the world of data science 🚀Satyam Agarwal @Satyam_Agarwal_
23 Followers 73 Following | Programmer | Data Analyst | Developer | Database Designer | Digital Marketing | Git |Little lemon for your.. @BluButterfly611
132 Followers 206 Following The TRUTH is like the sun, it ALWAYS comes out. 💚🤍❤️YD @DarkHidoura
2 Followers 32 FollowingGianne @HeleneGiannis
2 Followers 80 Followingzc w @zcw1034091
1 Followers 38 FollowingBindu Reddy @bindureddy
124K Followers 339 Following CEO of @abacusai, using Gen AI to build Applied AI and LLM agents and systems at scale, ex-AWS / Google, passionate about human behavior and open-source AGIAustin Zielman @austinzielman
89 Followers 39 Following Ready for general AI to deprecate the light switch.nandish tella @nandishtella
102 Followers 324 FollowingColin White @crwhite_ml
992 Followers 760 Following Automating, explaining, and de-biasing neural networks. Head of Research at @abacusai. Prev @SCSatCMUSam Nolen @SamRNolen
1K Followers 3K Following Machine learning, chess, languages, fiction, philosophy, history, cats, socialism. In recovery from ME/CFS, CCI, mold toxicityArvind Sundararajan @arvinds
774 Followers 325 Following CTO & Co-Founder @abacusai, ex UBER ATG, ex GoogleFIRST EVER Long Context (128K) Llama-3 70B - Llama-3-Giraffe-70B From Abacus AI The biggest issue with the Llama-3 family is that they are fairly small context models. So, even though they are as performant as GPT-4 on critical benchmarks, they can't be used in the real world…
AI Agents Are Going To Be Ubiquitous, And You Can Build Them Using The English Language The simple way to build AI agents is to simply specify what you want in the english language and then let the AI do the planning, coding, and building Write a detailed 2-3 line prompt, and…
The "Office Suite of AI" Bindu Reddy @bindureddy is founder/CEO of Abacus AI, a company that makes a suite of tools that you can use to turn your business into an AI-run workhorse. Here she talks to business people who are starting to implement AI, or are interested in learning…
The Private LLM guys made Llama-3-Smaug from Abacus available on their iPhone app. It's a very good small model... and works pretty well on a mobile device. Who would have thunk it? - LLMs running on your phone 🤯🤯
Complex Customer Support Agent by @abacusai ! Customer support go automated. AI create value for Businesses.
Create Complex Agents In Hours!! You can create a customer service agent and integrate it with your customer service software like Zendesk in hours... AI, not humans, build these agents on our platform
Create Complex Agents In Hours!! You can create a customer service agent and integrate it with your customer service software like Zendesk in hours... AI, not humans, build these agents on our platform
The average MT-Bench score of Llama3 is 8.04. The new model's score is 8.25. That's a large jump! And it only took a few days. The name of the model is Llama-3-Smaug-8B, and it was created by the team @abacusai. Here is the model in HuggingFace: huggingface.co/abacusai/Llama…
Building AI Agents - build agents to automate simple tasks - show ROI quickly - in the beginning, these agents will mostly be assistants to humans - agents that talk to internal systems, pull repeats, send emails and interface with you on slack / teams are the most popular -…
Please Stop Saying Open Source AI Makes No Money Takes claiming open-source AI and software are pointless because we live in a for-profit capitalist society make NO SENSE - Meta open-sourcing Llama is a strategic masterstroke and serves its business interests. The community…
MT-Bench Scores And Why They Matter? MT-Bench is an LLM benchmark that measures an LLM's ability to engage in coherent, informative, and engaging conversations. It is designed to evaluate the performance of LLMs in having conversations and following instructions - attributes…
🚨New GGUF alert! - 5x new high-quality IQ based quantized models for "Meta-Llama-3-70B-Instruct" by @AIatMeta - 10x new GGUF models for "Llama-3-Smaug-8B" by @abacusai Models are available on @huggingface (links are in the comments) - as always, thanks for the support ❤️
My conversation with the Wall Street Journal and the need for unbiased, liberated LLMs that don’t exercise thought control We at Abacus AI are working on several fine tunes in the space including agentic LLMs! Yes, they will be safe and no, they won’t have access to the…
Interesting topic @mims Anti-woke AIs and Agentic AI Nice to see @bindureddy and @abacusai introduce "Liberated Qwen" that will answer any question prioritizing it's learning first wsj.com/tech/ai/here-c… via @WSJ
Llama-3-Smaug-8B 🦙🐉 Finetuned from Meta-Llama-3-8B, build for improving performance on real world multi-turn conversations. via @abacusai @bindureddy @crwhite_ml @arvinds 👏 HuggingFace: huggingface.co/abacusai/Llama…
World's Best Small Model - Announcing Llama-3-Smaug-8b! - Significant MT-Bench improvement Imagine if a llama and a dragon had a baby! - We would have an altogether better model in the form of Llama-3-Smaug-8B!! The model is available on Hugging Face NOW and significantly…
@bindureddy Really good. Planning to explore @abacusai for data analytics.
Don't Buy Tableau or some other expensive tool... Just use an AI agent