Shishir Patil @shishirpatil_
CS PhD @ UC Berkeley. Creator of Gorilla, GoEx, RAFT, OpenFunctions and Berkeley Function Calling Leaderboard. Previously researcher @GoogleAI @MSFTResearch shishirpatil.github.io Berkeley, CA Joined July 2009-
Tweets189
-
Followers3K
-
Following850
-
Likes456
[1/5] Introducing Stylus 🖌️ - an #AI tool that automatically finds and adds the best adapters (LoRAs, Textual Inversions, Hypernetworks) to #StableDiffusion based on your prompt. 🗞️ Paper: arxiv.org/abs/2404.18928 🌎 Project Page: stylus-diffusion.github.io
@Dave_Ideate I'd say there are two big problems (a) LLMs can't provide any guarantees on their internal state and therefore a programmer cannot put bounds on correctness for state management. This has led to great work by @shishirpatil_ and team on GoEx. (b) RAG doesn't extend reasoning…
Excited to welcome Snowflake-Arctic on the Berkeley Function Calling Leaderboard ❄️ How does Snowflake-arctic-instruct, an apache-2.0 licensed, 480B parameter MoE model perform on invoking functions (aka tools)? Attached is a quick comparison with gpt-4-0125-preview (yellow).…
Important point
Under-appreciated leaderboard in my opinion - function calling (aka tool usage) is one of the most interesting applications of LLMs, plus it should be independent of how much "knowledge" is baked into the models
Under-appreciated leaderboard in my opinion - function calling (aka tool usage) is one of the most interesting applications of LLMs, plus it should be independent of how much "knowledge" is baked into the models
Check out how good is Llama 3 on tool calling 👀 Thorough work by @RickLamers on the Berkeley Tool Calling Leaderboard!
Check out how good is Llama 3 on tool calling 👀 Thorough work by @RickLamers on the Berkeley Tool Calling Leaderboard!
GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications arxiv.org/html/2404.0692… by Shishir G. Patil et al (UC Berkeley) and @martin_casado (a16z) This is a super interesting paper with the underlying thesis that “post-facto LLM validation” is a better…
🤩 Looking good 🦍👌😂
Hey @burkov, Thanks for featuring our work! We want to point out that our evaluation does not only measure the function choice accuracy; we do take into account the correct choice of parameters and their values. What’s more, in our Leaderboard April 1st release, we patched it to…
Hey @burkov, Thanks for featuring our work! We want to point out that our evaluation does not only measure the function choice accuracy; we do take into account the correct choice of parameters and their values. What’s more, in our Leaderboard April 1st release, we patched it to…
📢 Berkeley Function-Calling Leaderboard is amazing! It evaluates the LLM's ability to call functions (aka tools) accurately. There are proprietary and open models! I see Hermes 2 Pro ranking 20th 👀 Now I have to try Gorilla OpenFunctions v2! Thanks @shishirpatil_ and…
How to do better RAG? 🤔Check out in this webinar with @jerryjliu0 on the shortcoming of today's RAG 👀and how a few simple tricks to create a fine-tuning data-set can vastly improve performance for in-domain RAG! And thanks to @ravithejads RAFT is now already part of…
How to do better RAG? 🤔Check out in this webinar with @jerryjliu0 on the shortcoming of today's RAG 👀and how a few simple tricks to create a fine-tuning data-set can vastly improve performance for in-domain RAG! And thanks to @ravithejads RAFT is now already part of…
Thanks for sharing our work @arankomatsuzaki 🫡
Thanks for sharing our work @arankomatsuzaki 🫡
How are LoRAs and longer contexts for LLMs related? Check out @xiuyu_l and @sijun_tan's latest work on training LoRA adapters to support in-domain long-context 🗞️
How are LoRAs and longer contexts for LLMs related? Check out @xiuyu_l and @sijun_tan's latest work on training LoRA adapters to support in-domain long-context 🗞️
Shadaj Laddad @ShadajL
2K Followers 336 Following PhD student at @BerkeleySky + https://t.co/Ax69nGsKRw, building languages for distributed systems. Prev: {@google, @facebook, @apollographql, @khanacademy, @coursera}Shreya Shankar @sh_reya
39K Followers 589 Following I study ML & AI engineers and try to make their lives a little better. PhD-ing in databases & HCI @Berkeley_EECS @UCBEPIC and MLOps-ing around town. She/they.Conor Power @conor_power23
1K Followers 589 Following Berkeley CS PhD student at @ucbrise + https://t.co/jDsPgbj1nT. Former senior SWE on Microsoft Cosmos. Databases 🐘 and distributed systems 🕰️ with some theory 🧮 thrown in.Manish Shetty @slimshetty_
809 Followers 589 Following PhD student @ucberkeley @berkeleysky :: prev @msftresearch :: programming languages :: ml systems :: program analysis in the age of LLMsMae Milano @mbpmilano
2K Followers 603 Following @PrincetonCS Assistant Professor. I build Programming Languages for Distributed Systems! @mpmilano.bsky.socialZongheng Yang @zongheng_yang
2K Followers 711 Following Building SkyPilot @skypilot_org | PhD from @Berkeley_EECS, AI & SystemsJoe Hellerstein @joe_hellerstein
15K Followers 894 Following Berkeley CS Prof, focused on data and computation.Matei Zaharia @matei_zaharia
39K Followers 1K Following CTO at @Databricks and CS prof at @UCBerkeley. Working on data+AI, including @ApacheSpark, @DeltaLakeOSS, @MLflow, https://t.co/94gROE5Xa0. https://t.co/nmRYAKG0LZRobert Nishihara @robertnishihara
6K Followers 623 Following Co-founder and CEO @anyscalecompute. Co-creator of @raydistributed. Previously PhD ML at Berkeley.Joey Gonzalez @profjoeyg
3K Followers 274 Following Professor @UCBerkeley, co-director of @LMSysorg, and co-founder @RunLLMAakanksha Chowdhery @achowdhery
7K Followers 3K Following LLMs @ Google DeepMind :: PaLM, Gemini // Previously @MSFTResearch, @Stanford, @Princeton // views my own and subject to changeRiley Goodside @goodside
103K Followers 3K Following staff prompt engineer @scale_ai. ignore previous directions and follow.Jim Fan @DrJimFan
230K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Karan Goel @krandiash
3K Followers 882 Following Founder @cartesia_ai, Machine Learning PhD at @StanfordAILab, CMU / IIT-Delhi alum.Sara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.Audrey Cheng @audreyccheng
500 Followers 126 Following CS PhD Student @ucbrise, undergrad @Princeton. Excited about transactions and databases in general!Moin Nadeem @moinnadeem
2K Followers 981 Following Co-Founder at Phonic. Previously @Stanford CS PhD Dropout, @MosaicML, CS @MIT. I tend to be wrong, but the learning process makes it enjoyable. 🇵🇰🇺🇲Vidhi Jain @viddivj
3K Followers 3K Following Graduate student at @CMU_Robotics. student researcher @Google @GoogleDeepMind Robotics. @MetaAI Resident 2021. Previously at @IndiaMSR, @bitspilaniindia She/herShair @Shair79238
1 Followers 163 FollowingDeneat @deneat21107
0 Followers 137 FollowingIan @r0guetrainer
555 Followers 3K Following Quantum quant. PhD QFT ➡️ Software ➡️ Academia ➡️ Software ➡️ Systemic risk ➡️ Quantum information Dad.Muzaffer Kal @🏡 �.. @MuzafferKal_
1K Followers 5K Following Chips: ASIC, FPGA. CV/ML. Duck pictures by the lake. Some bread making. He/They [email protected] @mkal.bsky.social threads.net@muzafferkal_Samarth Mehta @iSamarthMehta
4 Followers 175 FollowingDavid Murgatroyd @dmurga
355 Followers 132 Following I love giving leadership to people, ideas, and tech that together empower meaningful experiences to improve lives. #MachineLearning #Personalization @SpotifyEngAl @Al7350712283221
1 Followers 211 FollowingKishore Chitrapu @kchitrapu
51 Followers 314 Following🕺💃🤟 Alexande.. @emaxerrno
4K Followers 2K Following Founder & CEO of @RedpandaData - A Kafka® replacement for mission critical systems. 10x Faster; Safe; API compatible. 🇨🇴Stefano Filippone @s_filippone
138 Followers 535 Following CTO | Bazar do Consórcio | Technology lover | Tech product designFANVince @FANVince
75 Followers 1K FollowingGuillaume Bouchard @gbouchar
427 Followers 279 Following AI Entrepreneur, Research Scientist and Investor. CEO and Co-Founder of Checkstep.Bhavya Kashyap @Bhavbhavbhav
1K Followers 259 Following Ex @Cocoon_HQ, @Amazon, @Microsoft, @Facebook — both eng and PM at various times. Now chillin @Chime. Founder of Oat Productivity.TechMachines @techmachines_
15 Followers 28 Following Make technology accessible to all by sharing basic tech knowledge. Build Technology by doing things.Yihe Deng @Yihe__Deng
2K Followers 1K Following CS PhD student @UCLA | Prev. Applied Scientist Intern @AWS | LLM, Multi-modal learningBanghua Zhu @BanghuaZ
2K Followers 804 Following PhD @Berkeley_EECS, statistics, info theory, LLM, RL, Human-AI Interactions.panyinxu @pnynx3
9 Followers 222 FollowingNelson Keating @nelson_keating
3K Followers 2K Following Build digital things 🛠 // Co-Founder https://t.co/NM2qhvI4fM https://t.co/XlN4XyuXqBRahul Thakur @raahulthakur30
116 Followers 2K Following VC | Startups | Generative AI | Product. I talk about anything that I find interesting.L Jenkins @XJPNMGB
14 Followers 146 FollowingGohans @GohansVN
79 Followers 717 FollowingPekka Brax @BraxPekka
44 Followers 216 Followingabtb @abtb168
319 Followers 5K FollowingElectronicsseeker @libertarian108
9 Followers 2K Followingvibin’-3.5-turbo �.. @nomoammo
36 Followers 528 Following 🌱 shared resonant frequencies / tweets are my own opinions unless they’re also your opinions, in which case, we can share them.pushkar @thepushkarp
156 Followers 472 Following generating shareholder value • ml + backend • writes https://t.co/MksNvISw1PBruno Soares Taveira @bstaveira
276 Followers 2K FollowingVikram @vikramkpatil
122 Followers 709 FollowingAruneshwar A R @AruneshwarAR
10 Followers 36 FollowingRahul @rahulkharwadkar
192 Followers 354 Following Technologist, Startup ex-entrepreneur, P&L leader, Semiconductor industrySarthak Pujari @SarthakPujari12
15 Followers 353 Following Currently interested in understanding the capabilities (and limitations) of AI | Hobbies : Eating good food and understanding national politicsMichael.G @MichaelBiGong
37 Followers 264 Following Manager of Data Science @ https://t.co/5xyE49254B Kaggle MasterJavi Martin @renaisserAI
587 Followers 85 Following Democratizing artificial intelligence in the enterprise world. @renaiss_ai || @aluxionlabsNingyu Zhang@ZJU @zxlzr
1K Followers 907 Following Associate Professor @ZJU_China. Research interests include NLP, KG.Shadaj Laddad @ShadajL
2K Followers 336 Following PhD student at @BerkeleySky + https://t.co/Ax69nGsKRw, building languages for distributed systems. Prev: {@google, @facebook, @apollographql, @khanacademy, @coursera}Shreya Shankar @sh_reya
39K Followers 589 Following I study ML & AI engineers and try to make their lives a little better. PhD-ing in databases & HCI @Berkeley_EECS @UCBEPIC and MLOps-ing around town. She/they.Conor Power @conor_power23
1K Followers 589 Following Berkeley CS PhD student at @ucbrise + https://t.co/jDsPgbj1nT. Former senior SWE on Microsoft Cosmos. Databases 🐘 and distributed systems 🕰️ with some theory 🧮 thrown in.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 🧠🤖💥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/q2Qoey80GxManish Shetty @slimshetty_
809 Followers 589 Following PhD student @ucberkeley @berkeleysky :: prev @msftresearch :: programming languages :: ml systems :: program analysis in the age of LLMsMae Milano @mbpmilano
2K Followers 603 Following @PrincetonCS Assistant Professor. I build Programming Languages for Distributed Systems! @mpmilano.bsky.socialZongheng Yang @zongheng_yang
2K Followers 711 Following Building SkyPilot @skypilot_org | PhD from @Berkeley_EECS, AI & SystemsYann 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.Joe Hellerstein @joe_hellerstein
15K Followers 894 Following Berkeley CS Prof, focused on data and computation.Matei Zaharia @matei_zaharia
39K Followers 1K Following CTO at @Databricks and CS prof at @UCBerkeley. Working on data+AI, including @ApacheSpark, @DeltaLakeOSS, @MLflow, https://t.co/94gROE5Xa0. https://t.co/nmRYAKG0LZPercy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistTalia 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 לכיבושJonathan Frankle @jefrankle
16K Followers 684 Following Chief Scientist, Neural Networks @Databricks via MosaicML. PhD @MIT_CSAIL. BS/MS @PrincetonCS. DC area native. Making AI efficient for everyone at @DbrxMosaicAIGeorge Porter @georgemporter
4K Followers 937 Following Computer Science Professor at @UCSD, focusing on networking and systems.Google DeepMind @GoogleDeepMind
944K Followers 275 Following We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.Doris Lee @dorisjlee
1K Followers 389 Following 🚀 Product @SnowflakeDB ⚡ Prev. Cofounder & CEO of @ponderdata 🎓 @BerkeleyISchool PhD, @IllinoisCS, Astro+Physics @BerkeleyPalmer Luckey @PalmerLuckey
219K Followers 2K Following I am a technology enthusiast, writer, and modder. Founder of ModRetro, @Oculus VR, and @Anduriltech. Keeping American superheroes safe with autonomous systems.Mike Maples, Jr @m2jr
84K Followers 7K Following Unearthing the mysteries of outlier startups. Partner @floodgatefund. Unabashedly grateful to live in the USA.Song Han @songhan_mit
6K Followers 144 Following Assoc. Prof. @MIT, Distinguished Scientist @NVIDIA, cofounder of DeePhi (now part of AMD) and OmniML (now part of NVIDIA). PhD @Stanford. Efficient AI computingSanjeev Arora @prfsanjeevarora
21K Followers 32 Following Director, @PrincetonPLI and Professor @PrincetonCS. Seeks math/conceptual understanding of deep learning and large AI models.Anna Riedl @AnnaLeptikon
6K Followers 5K Following nobody. Interested in cognitive science, rationality under radical uncertainty, complexity, systems, insight, meaning, synthesis, wisdom, information designVivek Raghunathan @vivek7ue
4K Followers 2K Following * AI + search at @snowflakedb. * Co-founder @Neeva (acquired by @snowflakedb). #NeevaAI = AI search engine with LLMs. * Ex-VP of Engineering @GoogleMelvin Johnson @melvinjohnsonp
980 Followers 280 Following Researcher @ Google Research. Multilingual NLP and MT. Previously, Stanford CS.buyhighsellhigher @ebitdaddy90
22K Followers 37 Following Ex p72/Citadel/GS. schooled in Boston. (she/her). Will adjust on ur ebitda until u free cash flow. PM (Portfolio Maestro), SS (Stock Shokunin), CFA (lvl9000).Sijun Tan @sijun_tan
95 Followers 239 Following CS PhD student @UCBerkeley @BerkeleySky | Working on secure AI and applied crypto | Prev: @AIatMeta @AntGroup @uva | https://t.co/PUN3YitVsZRoshan Sumbaly @rsumbaly
1K Followers 683 Following Herding Llamas and Emus in Gen AI @metaai. Prior life @coursera, @linkedIn, @stanfordMark Zuckerberg @finkd
760K Followers 747 FollowingSergey Edunov @edunov
953 Followers 103 Following Director of Engineering @ GenAI, Meta. I work on LlamasMike Lewis @ml_perception
6K Followers 227 Following Llama3 pre-training lead. Partially to blame for things like the Cicero Diplomacy bot, BART, RoBERTa, kNN-LM, top-k sampling & Deal Or No Deal.Harrison Chase @hwchase17
54K Followers 410 Following @LangChainAI, previously @robusthq @kensho MLOps ∪ Generative AI ∪ sports analyticsSergey Karayev @sergeykarayev
11K Followers 3K FollowingEric Hartford @erhartford
12K Followers 403 Following Principal Applied AI Researcher @TensorWaveCloud I make AI models Dolphin and Samantha https://t.co/3ri2GbXrQB BTC 3ENBV6zdwyqieAXzZP2i3EjeZtVwEmAuo4Zoe Kleinman @zsk
36K Followers 6K Following BBC Technology Editor, talking about tech on BBC TV, Radio + Digital. Also presenter, parent and occasional baker.Haotian Liu @imhaotian
6K Followers 397 Following building intelligence @xAI, creator of #LLaVA, cs @UWMadison, prev @MSFTResearchSasha Sheng 🫶🏼 @hackgoofer
4K Followers 2K Following Builder, Dancer; @aiengfoundation & on a mission to help people be well. Lover of hackathons and updating my beliefs. Staying grounded. Prev: @MetaAIJohnny Ni @JohnnyNi13
3K Followers 2K Following @Harvard - Prev. @northropgrumman @meta ML & Defense TechSherwin Wu @sherwinwu
15K Followers 518 Following Building the @OpenAI API – GPT-4, DALL·E, Whisper, TTS, Fine-Tuning, and more.Yangqing Jia @jiayq
12K Followers 263 Following Founder @leptonai. @UCBerkeley alumni. ex @google & @facebook. ex vp @AlibabaGroup. Open source work on caffe, @pytorch, @tensorflow, & @onnxai.Clémentine Fourrier .. @clefourrier
3K Followers 302 Following Leaderboards & evals research @HuggingFace 🐍✨ "The future is already here, it’s just not very evenly distributed" (Gibson)vLLM @vllm_project
785 Followers 11 Following A high-throughput and memory-efficient inference and serving engine for LLMsMartin Shkreli (e/acc.. @MartinShkreli
169K Followers 3K Following https://t.co/lzin5ByH0t [email protected] https://t.co/oMIiyJcIzk https://t.co/DuU6MMqcgQSolveig Gold @solveiggold
4K Followers 648 Following Cambridge PhD in Classics / “Princeton’s resident blonde Christofascist tradwife” 💁🏼♀️Pranav Shyam @recurseparadox
1K Followers 450 Following Research Scientist @DeepMind; ಕನ್ನಡಿಗ. Past: @OpenAI, @SchmidhuberAIDatabricks Mosaic Res.. @DbrxMosaicAI
30K Followers 115 Following We remove the barriers to state-of-the-art generative AI model development and make data + AI available to all.Charlie Cheng-Jie Ji @charlie_jcj02
78 Followers 515 Following Gorilla LLM, CS & DS @ UC Berkeley, Data 100 Lead TA, Working towards LLM Tool Use, AI safetyPamela Fox @pamelafox
25K Followers 177 Following (she/her) Currently a Principal Cloud Advocate in Python at Microsoft. @[email protected] Happy Pride! 🏳️🌈 🏳️🌈 👩🏽❤️💋👩🏼 👨🏼❤️👨🏿Sharad Vikram @sharadvikram
1K Followers 510 Following Researcher @ Google Deepmind. I work on JAX + Pallas (https://t.co/lPMsq3yzgL) and Gemini. In the past I worked on Oryx and TFP. I like learning.Corry Wang @corry_wang
25K Followers 254 Following Strategy @ Google | Formerly tech equity research @ Bernstein Research. All opinions expressed are my own, and do not represent Google'sKristina Shen @kshenster
8K Followers 563 Following GP @a16z, former BVP & Goldman. Boards of @muxhq @pavecomp @wrapbook @sprig @matik_io @rutterapi @heyequals . Mommy of 2 naughty boys 😜Mike Schroepfer @schrep
104K Followers 278 Following Partner @Gigascale, Sr Fellow (Formerly CTO) @Meta, founder @AdditionalVent, . Investing in tech and science to fight climate change. AIPriya Guha @UKPriyaGuha
9K Followers 1K Following Tech & Innovation/Ex-Diplomat/ @merianventures @future_planet @KheironMedical NED Reach plc @ukri_news @digicatapult & 🏸GB/ Multi-tasker & Mum 🇬🇧 🇮🇳 🇮🇹Tessa @tessybarton
601 Followers 750 Following Exploration agent. Research scientist at @MosaicML. Prev: @NYTimesReiner Pope @reinerpope
2K Followers 384 Following CEO and founder, @MatXComputing, developing high throughput chips tailored for LLMsHarvey Michael Pratt @npceo_
2K Followers 954 Following international man of leisure // https://t.co/69rOdEdkiqOliver Johansson @oliverjohansson
708 Followers 102 Following building @ucberkeley | prev cofo @whiteboardai, @rizz_ai (acq), @ZFellows_I'll be presenting the Neural Phishing Attack paper at #ICLR2024 next week, DM me if you want to chat! We'll be in "Halle B #220" at Thu 9 May 10:45 a.m. CEST (this is more for me to remember lol)
Fun, AI town coverage .... with a lot of good resources. ibtimes.co.uk/ai-town-simula…
@shishirpatil_ @luo_michael1234 @HelloCivitai @huggingface @brandontrabucco @bignamehyp @profjoeyg @rsalakhu Thanks @shishirpatil_ , we couldn't have done it without the #gorilla trailblazing S tier research!
[1/5] Introducing Stylus 🖌️ - an #AI tool that automatically finds and adds the best adapters (LoRAs, Textual Inversions, Hypernetworks) to #StableDiffusion based on your prompt. 🗞️ Paper: arxiv.org/abs/2404.18928 🌎 Project Page: stylus-diffusion.github.io
@Dave_Ideate I'd say there are two big problems (a) LLMs can't provide any guarantees on their internal state and therefore a programmer cannot put bounds on correctness for state management. This has led to great work by @shishirpatil_ and team on GoEx. (b) RAG doesn't extend reasoning…
Check out the latest Snowflake-Arctic's performance on the Berkeley Function Calling Leaderboard ❄️☃️
Excited to welcome Snowflake-Arctic on the Berkeley Function Calling Leaderboard ❄️ How does Snowflake-arctic-instruct, an apache-2.0 licensed, 480B parameter MoE model perform on invoking functions (aka tools)? Attached is a quick comparison with gpt-4-0125-preview (yellow).…
📢 [Berkeley Function Calling Leaderboard Update] Llama-3, Command-R-Plus, and Gemini-Pro-1.5 has been added to the family. We aim to provide a systematic, fair, and practical guide for the function calling capabilities of LLMs. Check out latency and costs at…
📊Delighted to welcome Command-R-Plus, Llama-3, and and Gemini-Pro-1.5 into the Berkeley Function Calling Leaderboard. Check out how they stack up across different categories, P95 latency, and costs at gorilla.cs.berkeley.edu/leaderboard.ht… Congratulations to @cohere, @AIatMeta, and…
Important point
This cost + latency for llama 3 is actually insane. Just look at the rest of the models in comparison
Under-appreciated leaderboard in my opinion - function calling (aka tool usage) is one of the most interesting applications of LLMs, plus it should be independent of how much "knowledge" is baked into the models
📊Delighted to welcome Command-R-Plus, Llama-3, and and Gemini-Pro-1.5 into the Berkeley Function Calling Leaderboard. Check out how they stack up across different categories, P95 latency, and costs at gorilla.cs.berkeley.edu/leaderboard.ht… Congratulations to @cohere, @AIatMeta, and…
Precisely 🫡
This is the prompt they are using for Llama-3 function calling (seems to work well even though it's not specifically fine tuned for that): github.com/ShishirPatil/g…
After a grueling few days of having to click accept to view the chatbot leaderboard, we put it back on HF :p huggingface.co/spaces/lmsys/c…
🫡 Checkout Command-R-Plus, Llama-3, and Gemini-Pro-1.5 function calling performance on Berkeley Function-Calling Leaderboard! 🔥 Amazing performance from Llama3 70B in multiple test categories! Come checkout the detailed breakdown in gorilla.cs.berkeley.edu/leaderboard.ht…
📊Delighted to welcome Command-R-Plus, Llama-3, and and Gemini-Pro-1.5 into the Berkeley Function Calling Leaderboard. Check out how they stack up across different categories, P95 latency, and costs at gorilla.cs.berkeley.edu/leaderboard.ht… Congratulations to @cohere, @AIatMeta, and…
A few (maybe obvious) challenges using LLMs within software applications I've seen as companies roll out their use: - versioning : While it's possible to tie a program to a specific model version, there is no structured way to handle new model versions (e.g. deprecation, sub…
The reception from the Llama 3 community has been wild. We think of future generations of Llama not just as a model, but an e2e system. Our work on Torchtune and Purple Llama are 2 early artifacts in our journey to open the higher layers of abstraction. More on this soon!
Already almost 1,000 llama3 model variations have been shared publicly on HF (many more in private use at companies): huggingface.co/models?sort=cr…. Everyone should fine-tune their own models for their use-cases, languages, industry, infra constraints,... 10,000 llama3 variants by…
Frontier level Tool Calling now live on @GroqInc powered by Llama 3 🫡 Outperforms GPT-4 Turbo 2024-04-09 and Claude 3 Opus (FC version) in multiple subcategories At 300 tokens/s 🚀 I've personally been working on this feature, and man, the new Llama is good!
A fun backstory: we first demoed this breakthrough to @finkd, @Ahmad_Al_Dahle and others this February on a single node. There was so much excitement about this research that in a mere 2 months we scaled it up and today is in production available to billions via Meta AI #movefast
In addition to Llama 3, today we’re also publishing a new paper: Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation ➡️ go.fb.me/g4r584 This work from GenAI researchers is enabling new image generation features in Meta AI on @WhatsApp & web.
I was curious how Llama-3 performs on my favorite math problem 🧮 I first encountered the problem at @CanUSAMathcamp mathcamp.org/2006/quiz/.
🦙 We're excited to host @Meta Llama-3 8b and 70b on Anyscale Endpoints! ➕ Fine-tuning, JSON mode and function calling support coming soon as well! Pricing: - 8B: $0.15 / Million tokens - 70B: $1.00 / Million tokens
So very excited for the promotion of @JenniferHli to GP. She's a primary reason @a16z enterprise investing is what it is, being a key player behind so many deals, our team and our investment philosophy and process. She really is "the best of us". a16z.com/jennifer-li/