-
Tweets45
-
Followers91
-
Following163
-
Likes252
✨New Paper Alert✨ Excited to introduce ExPO, an extremely simple method to boost LLMs' alignment with human preference, via weak-to-strong model extrapolation 👇 #LLMs #MachineLearning #NLProc #ArtificialIntelligence #AI
TL;DR: Unlike in language generation where multiple equally-acceptable outputs exist, each doc in GR is associated with a unique ID. If you miss one DocID token in beam search, you cannot recover. Solution: plan ahead in GR decoding! #SIGIR2024
TL;DR: Unlike in language generation where multiple equally-acceptable outputs exist, each doc in GR is associated with a unique ID. If you miss one DocID token in beam search, you cannot recover. Solution: plan ahead in GR decoding! #SIGIR2024
🤏 Why do small Language Models underperform? We prove empirically and theoretically that the LM head on top of language models can limit performance through the softmax bottleneck phenomenon, especially when the hidden dimension <1000. 📄Paper: arxiv.org/pdf/2404.07647… (1/10)
It's my first time to see GPT-4 loses to something else significantly.
✨🧬How can the process of scientific discovery be systematically automated to accelerate the expansion of the frontier of knowledge? We take a first step at answering this question in our new position paper. Very excited about this direction with some fantastic collaborators!!
✨🧬How can the process of scientific discovery be systematically automated to accelerate the expansion of the frontier of knowledge? We take a first step at answering this question in our new position paper. Very excited about this direction with some fantastic collaborators!!
Language model hallucinations are a big problem. Can we build LMs w/ factuality & correctness guarantees? Conformal factuality is a simple, practical modification to any LM that uses conformal prediction to give exact high-prob. correctness guarantees arxiv.org/abs/2402.10978
you knew the Softmax bottleneck, and that some classes might not be argmaxable... ...but did you know there is a Sigmoid bottleneck that __always__ makes an exponential number of label configurations unargmaxable? @Haw_Shiuan @andrewmccallum @ZihangDai @professorwcohen
you knew the Softmax bottleneck, and that some classes might not be argmaxable... ...but did you know there is a Sigmoid bottleneck that __always__ makes an exponential number of label configurations unargmaxable? @Haw_Shiuan @andrewmccallum @ZihangDai @professorwcohen
Canceling the anonymous period seems to suggest more and more NLP researchers worry about other people would do similar thing in the next few months. This might indicate it is much harder to have novel research ideas that satisfy most reviewers nowadays (e.g., by achieving STOA).
Canceling the anonymous period seems to suggest more and more NLP researchers worry about other people would do similar thing in the next few months. This might indicate it is much harder to have novel research ideas that satisfy most reviewers nowadays (e.g., by achieving STOA).
@murat_kocaoglu_ First one I always mention: I don’t think it makes sense for reviewers to be anonymous to other reviewers and meta-reviewers.
Most AI researchers try very hard to improve the performances and study why things works well, which is the necessary foundation of AI. OpenAI researchers try very hard to make sci-fi become reality and such craziness accelerates everything.
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions arxiv.org/pdf/2311.05232… The most comprehensive survey paper introducing LLM's hallucination causes and mitigations I have ever seen. I learnt a lot.
There is a dilemma. If we don’t have a standard LLM benchmark, researchers could just do some random changes and report the improvements on a selected subset of LLMs and datasets. If we have a benchmark, researchers would create lots of LLMs that only do well in the benchmark.
✨ New Paper ✨ Deep dive on demonstrations to enhance LLM-based passage ranking 🚀 insights for pointwise ranking using query likelihood 🚀 huggingface.co/papers/2310.14…
Jackie Dacosta @jack_dacos
43 Followers 5K FollowingChujie Zheng @ChujieZheng
507 Followers 494 Following LLM alignment and safety #LLMs | Visiting Scholar @CS_UCLA | PhD student @TsinghuaCoAI | he/him/hisArif Ahmad @arif_ahmad_py
274 Followers 7K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIWeeping fig @fig_weepin85029
12 Followers 477 Followingkumar @kumar__nn
0 Followers 1K FollowingHamed Zamani @HamedZamani
3K Followers 1K Following Asst. Prof. @manningcics. Assoc. Director of the Center for Intelligent Information Retrieval (CIIR). Ex-Researcher at Microsoft. Interested in IR, RecSys & ML.Andreas Grivas @andreasgrv
375 Followers 550 Following PhD Candidate in Natural Language Processing at the University of Edinburgh.BMR LLC @bmrllcinthe206
51 Followers 747 FollowingMaven Network @maven_network
59 Followers 285 FollowingAbhilash Koshti @AbhiPeerbits
20 Followers 476 Following IT Enthusiast | Empowering businesses through Innovative solutionsOmar Khursheed @omar_khursheed
262 Followers 1K Following Applied Scientist @Amazon Alexa, CS Masters - UMass Amherst, CE Undergrad - Aligarh Muslim University, Views my own | Narendra Modi is a fascistMunyeong Kim @Kim_Munyeong
594 Followers 1K Following 金文映/Moon-young. Kyungpook Nat'l Univ, South Korea. #HCI #AI S. Korea🇰🇷 and Mongolia🇲🇳. Simulating human behavior, interaction, and decision-making with AI.Aileen @vigap1972
27 Followers 540 Following As an enthusiastic and motivated cybersecurity and networking professional, I am committed to advancing my career and making a significant impact in the industrDhruvesh Patel @_dhruveshp
89 Followers 488 Following An @iitmadras graduate, Ph.D. student @umasscsJo Steve @MashedKale
3 Followers 258 FollowingNilanjan Sarkar @nilan_blue
368 Followers 4K Following Unlearning in LLMs| M.E CS @bitshyd| Applied Scientist intern @AmazonScience IML| #recsys #nlp #nlproc #clang #compilers #llvmArbaaz Qureshi @arbaaz__qureshi
332 Followers 2K Following Data Scientist @Lowes | Previously @Google and @MSFTResearch| CS grad @UMassAmherst and undergrad @IITPatNikhil Agarwal @scknyk
41 Followers 107 Following “Battle not with monsters, lest ye become a monster, and if you gaze into the abyss, the abyss gazes also into you.”Joe (Zhiyong) Xie @Joe_Xie
2K Followers 2K Following ML Platform Engineering @X. Alum: @Amazon, @Facebook, @Microsoft, @UW, and Nanjing Univ. Love tech, food and invest.Ameya Godbole @ameya_godbole1
151 Followers 250 Following PhD student @nlp_usc working on generalization and reasoning, prev @UMassAmherst, @iitg (he/him)I-Hung Hsu @IHung_Hsu
135 Followers 259 FollowingKarim Kamal @KarimAsh14
305 Followers 2K FollowingSIDI LU @sidilu_pluslab
142 Followers 130 Following Just a dumb bunny. Ph.D. Candidate @ UCLA Pluslab NLG/Generative Models/ML/RLCryptonagar @Cryptonagar1
41 Followers 728 FollowingAl Mamun @al_mamun_sardar
275 Followers 3K Following Looking for NLP/LLM related PhD positions | Research Assistant (NLP) at Jahangirnagar University | MSc (CS)Anjali Narayan-Chen (.. @anjalisaa
119 Followers 466 Following Applied Scientist @Amazon Alexa AI, PhD @IllinoisCS. I like NLP, conversational AI, cats, and video games.Shehzaad Dhuliawala @shehzaadzd
343 Followers 909 Following PhD student at @ETH_en | Previously Research Engineer @MSFTResearch Montréal | Master's at @UMassCS. He/HimAnanya Ganesh @ananya__g
254 Followers 228 Following Grad student at CU Boulder. Previously at ETS and UMass Amherst. Interested in machine learning and NLP research. she/they.Ryan David Cotterell @ryandcotterell
9K Followers 1K FollowingCanyu Chen @CanyuChen3
842 Followers 2K Following CS Ph.D. student @illinoistech | Truthful, Safe and Responsible LLMs | LLMs Meet Misinformation: https://t.co/up5sEN5r1gJiachen Zhao @jcz12856876
67 Followers 364 Following mscs @UMassAmherst, be @hkust. Going to apply for PhD in NLP/ML/ medical AI for the coming years.Xiang Zhou @XiangZhou14
397 Followers 624 Following Engineer @Google Bard ex Ph.D. at UNC-Chapel Hill (@unccs @uncnlp)Yufei Tian @yufei_t
565 Followers 539 Following CS PhD student @UCLA. Working on NLP, machine reasoning, creative/controllable NLG, commonsense, LLM eval. Intern @ai2_mosaic, @Amazon, undergrad @Tsinghua_UniAditya Srikanth @Adveerub
23 Followers 258 Following RE@Google DeepMind, LTI grad, BITSian. Here for the memes 🙂Vivek Gupta @keviv9
2K Followers 5K Following PostDoc @cogcomp UPenn | Ph.D. CS @UUtah | @iitkanpur. @Bloomberg & @MSFTResearch Fellow | ex-@MetaAI, @IBM, @Verisk, @samsungresearch, @Synopsys #nlp #mlDerek Tam @dtredsox13
141 Followers 196 Following PhD Student at UofT, Interested in Model Merging, Member of FBC Church.Dung Doan @dungdx34
201 Followers 5K FollowingRheeya Uppaal @RUppaal
302 Followers 184 Following CS PhD @UWMadison, working on aligned & generalizeable #NLProc. Former @GoldmanSachs, @UMassAmherst. Climate's friend with @project_wren.bagofwords.ai @bagofwordsai
282 Followers 4K Following All About NLP and Its Applications #safenlp #NLProc #ai #mlEvgeniy Volkov @evgvolkov
544 Followers 3K FollowingKartik Perisetla @kartikperisetla
301 Followers 2K Following NLP @Apple | Prev: @Microsoft AI Research, @LinkedIn | @CarnegieMellon | views are my ownMurali Manohar @gitlostmurali
153 Followers 1K Following Masters Student - Computational Linguistics - Europe ML Engineer @askui Previously @Gramener, IIIT Hyderabad.Lukas Strasser @lu_5t
59 Followers 1K FollowingChujie Zheng @ChujieZheng
507 Followers 494 Following LLM alignment and safety #LLMs | Visiting Scholar @CS_UCLA | PhD student @TsinghuaCoAI | he/him/hisNathan Godey @nthngdy
534 Followers 841 Following 3rd year PhD student @InriaParisNLP Working on the representations of language models, architectures, and pretraining methods https://t.co/CTHFx1ZqPoPan Lu @lupantech
4K Followers 1K Following PhD @CS_UCLA @uclanlp | Amazon/Bloomberg/Qualcomm/UCLA Fellows | Ex @Tsinghua_Uni @MSFTResearch @allen_ai @Adobe | #NLPoc, LLMs, Reasoning, AI4Math, AI4ScienceAllenNLP @ai2_allennlp
14K Followers 31 Following The AllenNLP team works on language-centered AI that equitably serves humanity. We deliver high-impact research and open-source tools to accelerate progress.Colin Raffel @colinraffel
30K Followers 655 Following nonbayesian parameterics, sweet lessons, and random birds. Friend of @srush_nlpSemantic Scholar Rese.. @ai2_s2research
571 Followers 23 Following Research team @allen_ai working on AI, HCI, ML, NLP, accessibility, and comp. social science in support of @SemanticScholar's mission of accelerating science.Tatsunori Hashimoto @tatsu_hashimoto
6K Followers 202 Following Assistant Prof at Stanford CS, member of @stanfordnlp and statsml groups; Formerly at Microsoft / postdoc at Stanford CS / Stats.Dan Jurafsky @jurafsky
27K Followers 297 Following Professor of linguistics and professor of computer science at Stanford and author of the James Beard award finalist "The Language of Food"Jordan Boyd-Graber @boydgraber
4K Followers 2K Following Trivia Nerd, NLPer, Dad, Colorado native in Maryland exile Working on QA, negotiating/cooperating bots, ML explanations Exemplar for absent-minded professorIvan Titov @iatitov
6K Followers 700 Following Professor of Natural Language Processing at Uni Edinburgh / Uni AmsterdamEdinburghNLP @EdinburghNLP
11K Followers 139 Following The Natural Language Processing Group at the University of EdinburghJHU CLSP @jhuclsp
5K Followers 664 Following Center for Language and Speech Processing at @JohnsHopkins #NLProc #MachineLearning #AI https://t.co/6IXR5OSiDY @[email protected]Dan Roth @DanRothNLP
2K Followers 54 Following VP/Distinguished Scientist, AWS AI Labs and the Eduardo D. Glandt Distinguished Professor, CIS, University of PennsylvaniaCognitive Computation.. @cogcomp
560 Followers 60 Following Dan Roth's Cognitive Computation Group at the University of Pennsylvania. (This is no longer the account of the Cognitive Computing Lab at Georgia Tech.)antonio vergari 💥 .. @tetraduzione
4K Followers 1K Following human being | associate prof in #ML #AI @ancAtEd | PI of #APRIL https://t.co/7uTqRZtmEd | #probabilistic #models #tractable #generative #neuro #symbolic |Andreas Grivas @andreasgrv
375 Followers 550 Following PhD Candidate in Natural Language Processing at the University of Edinburgh.Heng Ji @hengjinlp
4K Followers 236 FollowingSanjeev Arora @prfsanjeevarora
21K Followers 32 Following Director, @PrincetonPLI and Professor @PrincetonCS. Seeks math/conceptual understanding of deep learning and large AI models.zhou Yu @Zhou_Yu_AI
9K Followers 837 Following Associate Professor at Columbia, advancing the frontier of NLP. Forbes 30 under 30. Amazon Alexa Prize winner.Nikhil Agarwal @scknyk
41 Followers 107 Following “Battle not with monsters, lest ye become a monster, and if you gaze into the abyss, the abyss gazes also into you.”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/q2Qoey80GxDeepSeek @deepseek_ai
4K Followers 0 Following Unravel the mystery of AGI with curiosity. Answer the essential question with long-termism.Luke Zettlemoyer @LukeZettlemoyer
8K Followers 2K FollowingICML Conference @icmlconf
70K Followers 17 Following Int'l Conf on ML • July 21-27, 2024 (Vienna, Austria) • #icml2024 • Contact: https://t.co/6saHKWV01y • https://t.co/sFwmcQNWkElmsys.org @lmsysorg
37K Followers 172 Following Large Model Systems Organization. We created Vicuna and Chatbot Arena! Compare 30+ LLMs (GPT-4/Claude/Llamas) side-by-side at https://t.co/IDFeIDIOtmShikhar @ShikharMurty
1K Followers 127 Following PhD student at @StanfordNLP, @StanfordAILab. Ex: @GoogleDeepMind, @MSFTResearch Interested in structure and interpretation of human languageAntoine Bosselut @ABosselut
3K Followers 602 Following Helping machines make sense of the world. Asst Prof @ICepfl; Before: @stanfordnlp @allen_ai @uwnlp @MSFTResearch #NLProc #AIACLRollingReview @ReviewAcl
5K Followers 62 Following ACL Rolling Review. Deadlines 10/15, 12/15, 2/15, 4/15 Tweets by @mayhewsw, @gneubig, @karmake2, @zeeraktalat, & othersNAACL HLT 2024 @naaclmeeting
8K Followers 50 Following The official account of the Annual Conference of the North American Chapter of the Association for Computational Linguistics.UNC NLP @uncnlp
3K Followers 388 Following NLP (+ML/AI/CV) research group at UNC ChapelHill (@UNCCS @UNC). Faculty: @mohitban47+@gberta227+@snigdhac25+@shsriva+@tianlongchen4+@huaxiuyaoml + othersPeter Hase @peterbhase
2K Followers 691 Following Google PhD Fellow at @uncnlp. Interested in interpretable ML, natural language processing, AI Safety, and Effective Altruism.Sean (Xiang) Ren @xiangrenNLP
6K Followers 561 Following Building @SaharaLabsAI | @USCViterbi Early Career Chair, Professor @nlp_usc | @MIT TR 35 , @ForbesUnder30 | Prev: @allen_ai, @Snapchat, @Stanford, @UofIllinoisUSC NLP @nlp_usc
3K Followers 368 Following The NLP group at @USCViterbi. @DaniYogatama+@_jessethomason_+@jieyuzhao11+@robinomial+@swabhz+@xiangrenNLP at @CSatUSC + researchers @USC_ICT, @USC_ISI.Aristo Team at AI2 @ai2_aristo
783 Followers 9 Following Building machines that can read, learn and reason at @allen_ai Join us: https://t.co/U4rmyx7f1EAllen Institute for A.. @allen_ai
54K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLWilliam Wang @WilliamWangNLP
14K Followers 718 Following UCSB NLP Lab + ML Center. https://t.co/6TOnqbk6YT https://t.co/KJYhnav3Et Mellichamp Chair Prof. at UCSB CS. PhD @ CMU SCS. Areas: #NLProc, Machine Learning, AI.Swabha Swayamdipta @swabhz
6K Followers 461 Following Assistant Prof. @CSatUSC | Researcher in #NLProc | Previously with @uwnlp @allenai | she/herMunyeong Kim @Kim_Munyeong
594 Followers 1K Following 金文映/Moon-young. Kyungpook Nat'l Univ, South Korea. #HCI #AI S. Korea🇰🇷 and Mongolia🇲🇳. Simulating human behavior, interaction, and decision-making with AI.Aishwarya Kamath @ashkamath20
7K Followers 587 Following Research Scientist @GoogleDeepMind. PhD at NYUOfir Press @OfirPress
10K Followers 3K Following I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.Hanna Hajishirzi @HannaHajishirzi
6K Followers 328 Following Associate professor at @uw_cse; senior director at @allen_ai co-leading @allenNLP; AI/NLP researcher at @uw_nlpOur interdisciplinary law+stats paper got a perfect score 7M/5R yet still got rejected... @FAccTConference cannot claim to be an interdisciplinary conference if it adopts a peer review system which is systematically biased against interdisciplinary work!
Day2 happening now with @MaartenSap (Artificial Social Intelligence), @peterbhase (Interpretability, Model Editing, Scalable Oversight), @KathleenACreel (Algorithmic Monoculture & Ethics of Systemic Exclusion), @LakeBrenden (Classic Debates in CogSci with AI)! Day1 had a lot of…
🚨 Excited to announce the 'UNC Symposium on AI and Society'! 🙂 cs.unc.edu/event/symposiu… Excellent line-up of speakers (Apr25+26) across diverse disciplines/departments incl. computer science, philosophy, cognitive science, psychology, ethics, sociology, data science,…
As someone who spent 6 years working in this area and wrote an entire dissertation I wholeheartedly disagree that LLMs are as creative as humans.
I used to be a skeptic too. Sure, LLMs fall down on math & complex logic (as do lots of humans). They also learn w/o real world contexts. But they understand what's Relevant & respond appropriately! When it comes to lng, they seem to be as creative as humans
✨New Paper Alert✨ Excited to introduce ExPO, an extremely simple method to boost LLMs' alignment with human preference, via weak-to-strong model extrapolation 👇 #LLMs #MachineLearning #NLProc #ArtificialIntelligence #AI
TL;DR: Unlike in language generation where multiple equally-acceptable outputs exist, each doc in GR is associated with a unique ID. If you miss one DocID token in beam search, you cannot recover. Solution: plan ahead in GR decoding! #SIGIR2024
🔥A new milestone for Generative Retrieval on large-scale IR datasets! We propose a new GR framework-PAG, outperforming many SOTA dense retrieval models on MS MARCO 8.8M while only requiring x7.7 less index memory. Preprint: arxiv.org/pdf/2404.14600… Code: github.com/HansiZeng/PAG
So fun to have @mohitban47 over at @nlp_usc!, for his amazing talk on modelling, interpreting and planning in multimodal LMs. Loved chatting over a range of topics — reasoning, VLMs, academia and my favourite, GPU-rich vs. poor 😂
Looking forward to welcome @mohitban47 as a distinguished lecturer to @CSatUSC tomorrow and learn about his latest work on Multimodal LLMs: viterbi.usc.edu/calendar/?even… It's going to be a good day at @nlp_usc
Mesmerizing visualization of the softmax bottleneck in multi-label classification!
The softmax bottleneck is an interesting problem; it has many side effects which we do not yet fully understand! If you want to build an intuition for the problem, here is an interactive visualisation I made grv.unargmaxable.ai/static/files/s… (best viewed on desktop).
Check out our new #NAACL2024 paper that elicits and exploits cross-lingual ability from LLM to help zero-shot cross-lingual structure prediction tasks. We also demonstrate that the method is much better than prompting LLM to do cross lingual task directly.
🔍🚨How to improve multilingual performance on structured prediction tasks? Excited to share our latest work CLaP - a label projection technique utilizing LLMs to do contextualized machine translation, improving two tasks in 47 languages including 10 extremely low-resource ones!
Thank you for your response. I will keep my score.
Pleased to announce that I've joined @cohere (7 months ago...) Since then we've built a great model (excellent at RAG, tooluse and multihop reasoning) that we are releasing along with the weights today!
Announcing C4AI Command R+ open weights, a state-of-the-art 104B LLM with RAG, tooling and multilingual in 10 languages. This release builds on our 35B and is a part of our commitment to make AI breakthroughs accessible to the research community. 🎉 huggingface.co/CohereForAI/c4…
Remember AMR?🤭 Turns out, with its clear, structured representation of the semantic information in text, we can targetedly generate challenging negative examples with disguising hallucination to train automatic evaluators to spot them! #NAACL24
🔥 Unlocking the power of Abstract Meaning Representations, AMRFact generates coherent, factually inconsistent summaries with high error-type coverage to improve the factuality evaluation on abstractive summarization! 📣 Check out our new #NAACL2024🇲🇽work: arxiv.org/abs/2311.09521
I am thrilled to defend my PhD and finally earn the title of Doctor🧑🎓. It's been a truly rewarding journey at @UCLAComSci. I'm so fortunate and grateful for the invaluable mentorship from Prof. @kaiwei_chang @uclanlp. He has always been incredibly encouraging, helpful, and…
Congrats 🎉 to the newly titled Dr. Lu @lupantech on defending his thesis about mathematical reasoning with language models"! 🧮 Pan has published a series of works on quantifying and improving math and scientific reasoning ability in LLMs. Some highlights:
💡Can LLMs like GPT-4 reason creatively? Excited to share our latest research on AI and creativity! 🚀 Introducing MacGyver: a new playground for everyday innovation and physical reasoning --we collect problems to trigger unconventional usage of objects and innovative solutions.
Interested in using LLMs to summarize long books? Check out @YekyungKim's new paper evaluating faithfulness of the resulting summaries! TLDR: Claude-3-Opus is the best LLM we eval'd, and auto-raters of faithfulness are unreliable (unlike e.g. FactScore / BooookScore)
Summarizing long documents (>100K tokens) is a popular use case for LLMs, but how faithful are these summaries? We present FABLES, a dataset of human annotations of faithfulness & content selection in LLM-generated summaries of books. arxiv.org/abs/2404.01261 🧵below:
Summarizing long documents (>100K tokens) is a popular use case for LLMs, but how faithful are these summaries? We present FABLES, a dataset of human annotations of faithfulness & content selection in LLM-generated summaries of books. arxiv.org/abs/2404.01261 🧵below:
This is a must read... Totally raises the bar for what to expect out of long-context tasks and evals. Great job @YekyungKim and friends!
Summarizing long documents (>100K tokens) is a popular use case for LLMs, but how faithful are these summaries? We present FABLES, a dataset of human annotations of faithfulness & content selection in LLM-generated summaries of books. arxiv.org/abs/2404.01261 🧵below:
Please re-evaluate the author-reviewer dialogue and the rebuttal process at @icmlconf. Are they genuinely helping us as a community? CC's @rsalakhu @zicokolter @adrian_weller @kat_heller @nuriaoliver
Researchers often have to ask for recommendation letters for visa/job applications, etc. I wrote a script that allows you to find who cites your papers frequently to create a list of potential letter writers: github.com/neubig/researc… Hope it's helpful, improvements are welcome!
Here is a list of contributions from the @manningcics Center for Intelligent Information Retrieval (CIIR) to @SIGIRConf 2024! Multiple exciting papers on RAG, Generative Retrieval, Proactive Conversations, and LLM Personalization. Pre-prints coming up, stay tuned... #SIGIR2024
⭐️⭐️⭐️ Checkout DBRX, the new open source LLM from @databricks! ⭐️⭐️⭐️ I've only been here for a few weeks, but if there's one thing I've learned it's that this is a team that can execute on big and challenging projects while having a good time doing it. Glad to have played a…
Meet DBRX, a new sota open llm from @databricks. It's a 132B MoE with 36B active params trained from scratch on 12T tokens. It sets a new bar on all the standard benchmarks, and - as an MoE - inference is blazingly fast. Simply put, it's the model your data has been waiting for.