AI21 Labs
@AI21Labs
Followers
9K
Following
414
Media
102
Statuses
371
AI21 Labs builds Foundation Models and AI Systems for the enterprise that accelerate the use of GenAI in production. 🥂Meet Jamba https://t.co/xUBjKZHKVH
Joined August 2019
Introducing Jamba, our groundbreaking SSM-Transformer open model!. As the first production-grade model based on Mamba architecture, Jamba achieves an unprecedented 3X throughput and fits 140K context on a single GPU. 🥂Meet Jamba 🔨Build on @huggingface
37
246
1K
We released the #Jamba 1.5 open model family:. - 256K #contextwindow .- Up to 2.5X faster on #longcontext in its size class.- Native support for structured JSON output, function calling, digesting doc objects & generating citations . #AI #LLM #AI21Jamba
108
101
437
📄Jamba-1.5 whitepaper is out!.The whitepaper details the architecture, training schemes, novelties and in-depth evaluations of our new long context hybrid SSM-Transformer models - Jamba-1.5-Large and Jamba-1.5-Mini. Arxiv: Here are some highlights and
7
81
294
Today we’re launching AI21 Studio, a platform where you can instantly access our state-of-the-art language models to build your own applications - including a 178B parameters model, Jurassic-1 Jumbo. We can’t wait to see what you create! .
18
80
280
We just released Jamba-Instruct!. Built from our groundbreaking SSM-Transformer Jamba architecture, Jamba-Instruct brings the same technological innovation to the enterprise via an aligned model. With leading quality benchmarks, a 256K context window, and the most competitive
11
55
275
📄Jamba whitepaper is out!.The whitepaper details our in-depth ablations on this novel hybrid SSM-Transformer architecture, and how we chose to interleave Mamba, Transformer and MoE. Here are some highlights from the paper 👇1/6
3
61
252
Today we launched Jamba 1.6, the best open model for private enterprise deployment. AI21’s Jamba outperforms Cohere, Mistral and Llama on key benchmarks, including Arena Hard, and rivals leading closed models while maintaining unmatched speed and quality. Now available on
6
74
174
We are warning about scams being perpetrated by malicious actors falsely claiming to be AI21-related crypto/tokens. We explicitly clarify: AI21 has absolutely no connection, direct or indirect, to any cryptocurrency or tokens whatsoever. These cases have been reported to X and.
109
6
75
A language model that can talk to APIs? 😮 Say hello to Jurassic-X! 🦕🦕🦕 Read more on our blog, play with the demo, and sign-up for early access.
3
29
115
We're thrilled to announce that we've raised $155 million in series C funding, proudly joining the unicorn club with a valuation of $1.4 billion! 🦄.
9
21
100
Meet Maestro: @AI21Labs new AI Planning and Orchestration system. Unlike LLM-based agents, #Maestro ensures reliable outcomes while optimizing latency and cost. This is AI that you can actually trust. 🔗 Sign up now! #AI21Maestro #AccuracyAtScale
1
26
97
Come join us at #SFTechWeek! Sign up now:
🎉 Big news! The official calendar of events for #SFTechWeek and #LATechWeek is now LIVE!. And thrilled to announce that this is officially our BIGGEST Tech Week, ever!. - 850+ events 🤯.- San Francisco: Oct 7-13 🌉.- Los Angeles: Oct 14-20 🌴. Link to register below to see all
70
2
48
Jamba Mini 1.6 outpacing Gemini 2.0 Flash, GPT-4o mini, and Mistral Small 3 on output speed. .This is what fast looks like! #BuildOpen #AI21Jamba
2
3
69
1
8
66
Exciting news! 📣 We've launched Jurassic-2 and our task-specific APIs! Both are major game-changers, with Jurassic-2's new and improved capabilities, and our APIs' plug-and-play reading & writing functions that outperform competitors. Read more:
2
11
50
Our Series C round has not only met but exceeded expectations - with an extension of $53.5 million, bringing the total amount of this round to $208 million! 📈 .Special thanks to our latest investors @intelcapital and @ComcastVentures for joining us on this exciting journey.
2
6
49
Jamba support is now live on vLLM 🎉.Due to its novel hybrid SSM-Transformer arch, Jamba didn’t work out-of-the-box in vLLM. our own @MorZusman worked together with @vllm_project to integrate Jamba for an efficient serving in vLLM 🙌.
3
6
52
Our team had a blast at the @agihouse_org agents hackathon yesterday in the Bay Area with @LangChainAI, @GroqInc , @DeepLearningAI & @AndrewYNg. Our new Jamba 1.5 models are optimized for agent creation with a ton of built in features like:.- Function calling.- Structured JSON
4
9
48
We know that Jamba 1.5 models are the fastest, but the question is - how fast? @ArtificialAnlys tested our models to find out 😎The image below shows the throughput for various models (with prompt length = 10K tokens). Jamba 1.5 models are a whole lot faster – and that speed
22
4
29
We’re excited to share our latest innovation with the world and have it launch today on @ProductHunt!. Introducing our latest gaming experiment, “Human or Not?” - the first ever Social Turing Game. 👾
7
12
45
We’re thrilled to announce that Jamba-Instruct will soon be launching on @Snowflake Cortex AI!. “With AI21's groundbreaking Jamba-Instruct offered in Cortex AI, our customers will now be able to seamlessly connect their data to build transformative GenAI applications with AI21's
2
6
36
But our cost, efficiency and speed don't come at the expense of quality. In the following chart, Jamba 1.5 Large and Mini both show a great balance between speed and quality (QI is where you want to be). >>
34
1
19
Thanks @tri_dao! We enjoyed the opportunity to extend and build on top of Mamba. The Jamba white paper is coming soon and has some ablations we will share on this subject.
Wow this is a big deal, first large-scale Mamba-based model! Mamba layers brings much longer context and higher inference throughput. Having 4 attention layers seem to be the sweet spot to get the best of Transformer & Mamba architectures.
0
1
33
We’re excited to announce that our new course, ‘Build Long Context AI Apps with Jamba’, built in partnership with @AndrewYNg @DeepLearningAI is now live - and it’s currently free! . In this course, Chen Wang and Chen Almagor from AI21 Labs will walk you through how to use.
17
3
28
Find our new model on @huggingface.
Jamba released! @AI21Labs just released the first production-scale Mamba implementation! Jamba is a hybrid SSM-Transformer MoE rivaling open transformer-based LLMs 🚀. TL;DR:.🧠 52B parameters with 12B active during generation.👨🏫 16 experts with 2 active in generation.🆕 New
0
3
28
1/n Introducing J1-Grande, the newest member of the Jurassic-1 family. With 17B parameters, Grande offers Jumbo-like quality (10x larger) at an affordable price (⅓ of the cost).
2
11
30
Excited to share that our paper, Jamba: Hybrid Transformer-Mamba Language Models, has been accepted to ICLR 2025!. We’re honored to contribute to this important platform and the collective knowledge of the AI community by sharing our work openly and submitting it for peer review.
1
7
28
And 140K context on a single GPU. @ArtificialAnlys We look forward to seeing those benchmarks!.
Jamba model launch takeaways - Potentially a new leader for ultra-long prompt use-cases (RAG). ‣ First open-source model of this size to combine MAMBA state-space model architecture, Mixture-Of-Experts (MOE) and the transformer.‣ 256k context window, more than 2X the size of
0
1
26
We are beyond excited to have won Startup of the Year at the #GeektimeAwards! A huge thank you to our amazing team and to @geektime for this honor and recognition. This is only the beginning for us! 🏆
1
5
26
@Grad62304977 Jamba-1.5-Mini's architecture is the same as Jamba. We scaled up the architecture for our Large model. Our technical paper will be posted on in the next few hours.
1
1
22
Building a RAG solution is easy. Building a great one is not. In our guest blog on @streamlit, our team explores the intricacies of how AI21's Contextual Answers Task-Specific Model & our RAG Engine generate context-based answers grounded in your proprietary organizational data.
0
2
26
We're thrilled to announce our partnership with Amazon for their latest service, Bedrock. As our Co-CEO, Ori Goshen, stated, "With Jurassic-2 models and Bedrock, developers can maximize the performance of language tasks while optimizing the cost.".
0
5
24
Honored to be named among the top 3 most promising startups of 2023 by @Calcalist, and proud to be at the forefront of the #GenAI revolution! Thanks to Calcalist for this incredible recognition. Read more about the top 50 startups:
1
2
21
Congratulations to our chairman, Prof. @AmnonShashua, on being awarded the Israel Prize for lifetime achievement! 🏆This is a remarkable accomplishment and truly well-deserved. #MachineLearning #IsraelPrize #LifetimeAchievement
0
0
21
High throughput itself is never enough; it's all about optimizing the speed-cost-quality triangle. Thanks to Jamba’s architecture, we offer high speed at a very competitive price (in the image below, QII is where you want to be). >>
21
0
10
We're excited to introduce Contextual Answers, an API solution where answers are based on organizational knowledge, leaving no room for AI hallucinations. 💭. ➡️
0
4
18
(2/4) Jamba-Instruct outperforms or rivals other instruction-tuned competitors across common performance benchmarks.
1
0
19
Live from the @agihouse_org it’s the first ever Jamba hackathon! What long context use cases would you want to build with Jamba’s 256k context window?
0
2
18
Big thanks to our friends over @GoogleCloud_IL for sending us this sweet surprise after our latest round of funding! .Here's to a great partnership and many more celebratory treats to come! 🎂
2
0
18
Introducing the Jamba 1.5 Model Family on @googlecloud's Vertex AI:. - Simplify development and evaluation with advanced tools and intuitive API calls. - Focus on innovation with fully managed infrastructure and cost-effective, pay-as-you-go pricing. - Ensure data security with.
3
3
16
Recent evaluations show that our summarize API outperforms OpenAI's models, offering a better user experience and more consistent results. 📈 . Learn more about the research and findings 👇
1
3
17
We’ve been named one of the top 100 most innovative AI startups of 2022 by @CBinsights !. We are proud that our language models take part in pioneering this momentous period in AI history, and we look forward to shaping the future of NLP as an intelligent thought partner.
0
4
17
(4/4) With a 256K context window, Jamba-Instruct boasts the largest context window in its size class.
3
0
17
Hack by popular demand! .Open-Source Agent #Hackathon with @AndrewYNg & @DeepLearningAI at @agihouse_org Saturday, *August 24th*. Stellar schedule planned w/ secret guest speakers, alongside co-hosts, @GroqInc & @LangChainAI. Reserve your spot now -->
1
7
16
Want to test it yourself? Both models are available at 🤗 Check them out:
9
1
12
1/n Hot off the press – AI21 Studio graduated from Beta!! Seamlessly train your own custom model by the touch of a button using our enhanced user interface.
1
3
16
(3/4) Jamba-Instruct results on long-context QA benchmarks, conducted using the same method outlined in section 5.2.2 of our Jamba base model whitepaper.
3
1
16
To support efficient serving of Jamba-1.5-Large, we developed a novel quantization technique - ExpertsInt8. We quantize the MoE and MLP weights to INT8 in order to store them, and dequantize them back to BF16 before the actual computation. This technique is both very fast and
2
1
15
"Humans or Not" has become the largest Turing Test in history, with 1.5 million participants from around the world. 🌎. 💡 Uncover the fascinating insights and surprising strategies:
2
2
14
We wanted to share some more granular details about the Jamba 1.5 model family - and specific benchmarks on latency, context window, and quality. [1/6].
1
0
15
Today we announced the launch of our first product @wordtune, an #AI based tool that understands both writing & meaning. Check out our new writing assistant on @googlechrome, and read more on the announcement from @jeremyakahn in @FortuneMagazine:
0
4
14
It was an incredible experience to be a part of the START Global Summit in St. Gallen! . Our Co-CEO, @origoshen, had the opportunity to discuss the future of #GenerativeAI and the AI21 labs journey with the brightest minds and leaders in the industry. #START23 #ai #innovation
0
0
15
@huggingface 📄The Jamba whitepaper details our in-depth ablations on this novel hybrid SSM-Transformer architecture, and how we chose to interleave Mamba, Transformer and MoE.
0
3
13
SenseBERT: Pre-training with a novel self-supervised word sense prediction task improves #BERT's lexical semantics abilities, achieving a state-of-the-art score on the notorious Word-in-Context task. @tpilehvar #SuperGLUE #WordNet #NLProc #deeplearning
0
7
14
Last chance to sign up for the #Open-Source #Agent #Hackathon with @AndrewYNg at the @agihouse_org!. Hack with the movers-and-doers of Gen-AI from @DeepLearningAI, @GroqInc, @LangChainAI, and of course, some of the builders of #Jamba from @AI21Labs. 🔗
0
0
13
Interview with our Co-Chief Scientist, @YoavLevine: "When someone creates content, they want to be comfortable to put their name on it. And in certain use cases, the ability to connect the content to sources really facilitates this” via @bdtechtalks.
0
6
14
Jamba-1.5 models perform well in multiple languages, even though we include only a very small fraction of non-english data in the post-training phase. Therefore, we speculate the models are able to use the learned multilingual capabilities from the pre-training phase. 6/7
2
0
13
We found our efficient Jamba architecture to be advantageous in long context fine-tuning, as it allows for greater speed and lower cost. Therefore, we could experiment with multiple different training recipes during the fine-tuning phase. This is especially interesting for all.
0
1
14
Our Co-founder & Co-CEO @origoshen kicking off @awscloud #reInvent2022 with an exciting announcement: you can now deploy our LLM Jurassic-1 on your private SageMaker environment!
0
1
14
The hybrid Jamba architecture enables Jamba-1.5 models to reach excellent throughput and latency, especially at long contexts. With the same hardware, Jamba-1.5 models are the fastest across the board (in the image: 2xA100 80GB GPUs for Mini, 8xA100 80GB GPUs for Large). 2/7
1
2
13
Be sure to drop by booth 223 at this year's SaaStr Annual event! Explore the remarkable capabilities of AI21 Studio and discover how you can can easily customize language models to meet your specific needs. #ai21studio #saastr2023 #NLP
0
3
13
"Generative anything is the idea that you put in a little and get a lot. It's exciting as it is wondrous". Check out this recent CTech interview with our Co-Founder & Co-CEO, Prof. Yoav Shoham:
0
1
13
Our Co-Founder & Co-CEO, @yshoham will participate in @EntreeCap's panel discussion on #GenerativeAI. You are welcome to join!
0
1
13
Excited to share our latest case study on Verb, a new AI writing tool powered by AI21 Studio! . With the use of our custom models, Verb goes beyond mere text generation and becomes a true partner to authors everywhere.
1
4
13
We’re excited to share Auxiliary Tuning - a simple and efficient method for reducing training costs by adapting a pre-trained LM to a novel task, e.g. conditional text generation. #NLProc #DeepLearning.
0
3
12
We're shifting the paradigm of how to scale text-based AI applications affordably & efficiently. Read about our custom models approach and learn how to take your app from prototype to production.
0
4
12
Our friends at Verb have launched their AI-enhanced writing apps for authors. It's been a pleasure working with their wonderful team! 🥳.
Today, we’re thrilled to launch Verb, an AI-enhanced writing app for fiction writers! ✍️🤖. Verb helps you write, brainstorm, plan, and get feedback on your work. Sign up for free at . Read on for more on our thinking 👇🧵
0
0
11
Today at @nvidia GTC! ⚡ Join AI21 Labs’ co-founder and co-CEO @origoshen as he takes the stage to discuss the transition from reasoning models to AI planning systems. If you’re attending, let us know in the comments!
1
0
10
Spotted! Our awesome Co-CEO @origoshen on a billboard (!!!) in Tel Aviv. Thanks @Google - we ❤️ you too.
0
2
11
Our CEO @origoshen on live stage at #humanx2025 presenting #AI21Maestro AI21’s new approach to structured, multi-step AI execution. Finally, AI that follows and executes a plan. Thanks @stefanweitz and #HumanX team for inviting us.
2
2
12
We experimented with alternatives to our final Jamba architecture, including Mamba-2 (which was released a few months after the original Jamba). However, we found that in a hybrid architecture, the Mamba-1-Attention combination outperforms both Mamba-2-Attention and pure Mamba-2.
2
1
10
Our very own @GalShachaf will be presenting at #awssummit in Tel Aviv next week to speak about what we're developing here at AI21 Labs and how we use Amazon SageMaker to train large language models. You can register for the summit in this link:
0
1
11
Our VP of Platform @DanPadnos is speaking at @JohnSnowLabs NLP Summit this Thurs, Oct 7th at 2p EST. Come learn more about AI21 Studio & Jurassic-1!.
0
4
11
On Saturday, we hosted our first Bay Area hackathon at @agihouse_org, inviting devs to build apps with #Jamba. After 8 hrs of intense coding, each team presented a live demo leveraging Jamba’s massive 256K context window. 👇 Here are the highlights
1
2
9
2/n We built a poet and didn’t even know it. We requested a witty poem about the relationship between feline and canine. Here is what the J-1 master sonneteers composed:
1
0
11
Have you heard the news? we're now offering Jurassic-1 Grande on Amazon SageMaker! Check out the blog post and sign up for the preview:. #generativeai #aws #largelanguagemodels #nlp #ai.
Great #reInvent2022. Really enjoyed co-speaking with @GalOshri and Emily Webber in our session on distributed training and LLMs yesterday. Monday we announced that @AI21Labs Jurassic-1 is now available on @awscloud SageMaker. And today we’re already hearing from eager customers!
0
1
10
Among all publicly available and proprietary models, Jamba-1.5 models are the only ones with an effective length of 256K tokens, as evaluated by the RULER benchmark. 5/7
2
1
10
3/n Ready to meet the new kid on the block? Check out the blog post:
0
0
11
"LLMs change the way we can access information and that enables exciting possibilities for retailers." 🛒. 🎙 Tune in to find out how LLMs are transforming the eCommerce game: . #llm #ecommerce #retail #aibusiness.
0
0
10
Today! Twitter Spaces discussion on best practices for deploying LLMs, led by @percyliang with our very own.@Udi73613335 and other industry partners. See you there!.
Join us tomorrow (Wed) at 12pm PT to discuss the recent statement from @CohereAI @OpenAI @AI21Labs on best practices for deploying LLMs with @aidangomezzz @Miles_Brundage @Udi73613335. Please reply to this Tweet with questions!
1
2
11
The possibilities of AI in game development are endless. 🎮. Learn how Ubisoft harnessed the power of our AI to revolutionize their game creation process and achieve more in less time: . #gamedevelopment #AI #llm.
0
0
11
Catch our Co-CEO @origoshen in the closing panel at the AWS Startup Showcase on March 9th! They'll be discussing the hottest trend in tech - the future of Generative AI 🔥 Join this virtual event here: #GenerativeAI #TechTrends #LeadershipAdvice
0
2
11
We just posted a brief overview about the cost of training #NLP language models: @Or_Sharir @pelegbarak @yshoham.
0
4
10
Thanks @togethercompute - we're exciting to be making our Jamba models available on Together AI soon!.
Massive congratulations to our partners at @AI21labs on the release of their Jamba 1.5 models. Jamba 1.5 is a game-changer for long context and RAG:. - 256K context window.- 2.5x faster on long contexts.- JSON output, function calling, citation mode. Open innovation at its.
0
0
9
