Shishir Patil @shishirpatil_ Twitter profile

Pinned Tweet

Shishir Patil

1 year

📢 Excited to release Gorilla🦍 Gorilla picks from 1000s of APIs to complete user tasks, surpassing even GPT-4! LLMs need to interact with the world through APIs, and Gorilla teaches LLMs APIs. Presenting Gorilla-Spotlight demo🤩 Webpage:

32

206

975

Last Seen Profiles

@therealmrsteak

@2kasel

@DogStricken

@cottonclubjapan

@kyle_corso

@PVFCeSports

@MedBrad_

@UmKhonde

@wor_bn

@LIFAair_FI

@WelfordPrimary

@KIMDOYOUNGCSE

@RyleighLynn1

@GuilhermeIC

@Rengongmeng

@aberdoveyswim

@arzuahm46748265

@Rengongmeng

@MaddoxLee20

@Vertige__

@FMUSPoficial

@thesissysister

@echepaalla

@akram_samia

@Ururi_Rapis

@iroha2013

@Trofi_Official

@GEcologie

@asupanmu88

@yassportsTV

@rileedrew_

@realGollumTrump

@KalmanLiebskind

@heinuilecaill

@rickgoodman613

@_stephsgomes

Shishir Patil

@shishirpatil_

6 months

📢 Introducing Gorilla OpenFunctions! 🔥 We've listened to your calls for an open-source function calling model, and are thrilled to present Gorilla OpenFunctions 🦍 And yes, we've made parallel functions a reality in open-source! 😎 Curious about typical scenarios where GPT-4

11

60

317

Shishir Patil

@shishirpatil_

21 days

📊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 Congratulations to @cohere , @AIatMeta , and

12

62

323

Shishir Patil

@shishirpatil_

3 months

📢Excited to release the live Berkeley Function-Calling Leaderboard! 🔥 Also debuting openfunctions-v2 🤩 the latest open-source SoTA function-calling model on-par with GPT-4🆕Native support for Javascript, Java, REST! 🫡 Leaderboard: Blog:

9

68

300

Shishir Patil

@shishirpatil_

1 month

📢Excited to release GoEx⚡️a runtime for LLM-generated actions like code, API calls, and more. Featuring "post-facto validation" for assessing LLM actions after execution 🔍 Key to our approach is "undo" 🔄 and "damage confinement" abstractions to manage unintended actions &

6

53

203

Shishir Patil

@shishirpatil_

2 months

🌀Check out RAFT: Retrieval-Aware Fine Tuning! A simple technique to prepare data for fine-tuning LLMs for in-domain RAG, i.e., question-answering on your set of documents 📄 Exciting collaboration with @berkeley_ai 🤝 @Azure 🤝 @AIatMeta MSFT-Meta blog:

Tianjun Zhang

@tianjun_zhang

2 months

📢 Excited to release RAFT: Retriever-Aware FineTuning for domain-specific RAG, a three-way collaboration between @berkeley_ai @Azure and @AIatMeta ! 🤝 Drawing parallels between LLMs and students in open-book (RAG) 📔 and closed-book exams (SFT) 🧠, we present a better recipe

6

49

231

4

43

169

Shishir Patil

@shishirpatil_

11 months

🦍Introducing the all-new gorilla-cli, now available as a pip package!✍️ With a vast collection of ~1500 🆕APIs, including 👀 Kubernetes, AWS, GCP, Azure, GitHub, Conda, Curl, Sed, and more🤩 simply state your goal, and let Gorilla CLI generate the commands for execution.

5

29

148

Shishir Patil

@shishirpatil_

2 years

Train BERT on Smartphones 🤩 Announcing POET 📢 Find out how we train memory-hungry SOTA models on smartphones! #ICML2022 Thu 21 Jul 3:45 pm EDT at Room 327 🧵👇 Paper: Web:

6

34

134

Shishir Patil

@shishirpatil_

2 months

🏆New Leader Alert: @AnthropicAI 's Claude-3 tops our Berkeley Function Calling Leaderboard! 📊 Exciting updates include: ⏰Latency and cost for understanding trade-offs💲 🆕Explore new additions like - Claude-3 Haiku, Sonnet & Opus, @DbrxMosaicAI DBRX and more! ⁉️Dive into our

4

18

122

Shishir Patil

@shishirpatil_

1 year

🦍Big news! Gorilla is now Apache 2.0 licensed🤩We are delighted to welcome 2 new models into the Gorilla family ⛳️Use commercially with zero obligations! Our colab has been used for 6000+ invocations in the last week 🚀Check it out:

4

23

101

Shishir Patil

@shishirpatil_

1 month

🙇‍♂️ Humbled to have @AndrewYNg talk about Gorilla 🦍 This is the most succinct write up on tool-use and function-calling. When we started Gorilla back in January of 2023, this was precisely our hypothesis 🙂

Andrew Ng

@AndrewYNg

1 month

Tool use, in which an LLM is given functions it can request to call for gathering information, taking action, or manipulating data, is a key design pattern of AI agentic workflows. You may be familiar with LLM-based systems that can perform a web search or execute code. Some of

78

324

2K

2

8

83

Shishir Patil

@shishirpatil_

1 year

+ We are building Gorilla to be an LLM API appstore - you can add your APIs to Gorilla! + Github: + Join our Discord to stay in the loop! + Gorilla-Spotlight sign-up: + Fun collaboration with @tianjun_zhang , @xinw_ai and @mejoeyg

🦍 Gorilla Spotlight 🚀

Gorilla is a LLM trained by UC Berkeley and Microsoft Research that can pick from 1000s of APIs to perform user tasks. Inspired by the techniques from this research, we have built Gorilla-Spotlight...

docs.google.com

8

10

64

Shishir Patil

@shishirpatil_

20 days

Berkeley Function Calling Leaderboard: Introducing Consistent 8 X V100 with pay-as-you-go pricing for measuring costs and latency. In depth: We fix inconsistency in the cost and latency calculation for open-source models, which are now all calculated when serving the model with

Shishir Patil

@shishirpatil_

21 days

📊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 Congratulations to @cohere , @AIatMeta , and

12

62

323

2

14

61

Shishir Patil

@shishirpatil_

1 month

We study the inherent challenges in relying on LLMs—addressing their unpredictability, the essential trust mechanisms for their decision-making, and hurdles in failure recognition & resolution. Our system, GoEx presents abstractions and policies to overcome these for RESTful

5

19

55

Shishir Patil

@shishirpatil_

1 year

API invocations are extremely brittle requiring LLMs to generate accurate input arguments. Gorilla improves accuracy while reducing hallucination, and generalizes to 1600+ APIs (and counting). 📢 Given recent debates, we also find Fine-tuning >> Prompting.

2

10

44

Shishir Patil

@shishirpatil_

1 month

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

LlamaIndex 🦙

@llama_index

1 month

🎥 ICYMI: Check out the recording of our latest LlamaIndex Webinar on retrieval-augmented fine-tuning (RAFT)! In the webinar, @tianjun_zhang and @shishirpatil_ , the lead co-authors of RAFT, explain how combining an “open-book exam” approach (RAG) with a “closed-book exam”

2

31

136

2

7

44

Shishir Patil

@shishirpatil_

7 months

🤩Check out our latest release MemGPT 🦙📚 Inspired by how OS manages pages, we explore - can the LLM manage it's own context length, and page-out / page-in from archival memory?

Charles Packer

@charlespacker

7 months

Introducing MemGPT 📚🦙 a method for extending LLM context windows. Inspired by OS mem management, it provides an infinite virtualized context for fixed-context LLMs. Enables perpetual chatbots & large doc QA. 🧵1/n Paper: GitHub:

9

107

465

3

4

39

Shishir Patil

@shishirpatil_

1 month

Excited to see @cohere 's new Command R+ model's focus on tool use capabilities! Function Calling / Tool use has become a deciding factor in choosing models as we move beyond simple chatbots into integrating LLMs in workflows and agents. Check out our live Berkeley Function

Aidan Gomez

@aidangomez

1 month

R+ is quite performant. It's very competitive with models in its price range, and sometimes even those in a category above. Tool Use is a place we've seen considerable improvement in R+ over R.

2

5

89

0

6

39

Shishir Patil

@shishirpatil_

8 months

The last time @profjoeyg interviewed me, it was for PhD admissions to Berkeley.. Thankfully the stakes were lower this time 😜 Check out the latest interview where @tianjun_zhang and I dive into the details as we discuss #GorillaLLM and LLM APIs 🦍🦍🦍

Vikram Sreekanti

@vsreekanti

8 months

Gorilla's a super cool LLM application: You can autogenerate API calls for things like Kubernetes or transformers. 🛠️ @profjoeyg interviewed @shishirpatil_ & @tianjun_zhang about how the model works:

1

13

41

2

3

38

Shishir Patil

@shishirpatil_

19 days

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).

0

10

36

Shishir Patil

@shishirpatil_

1 year

Our unique Abstract Syntax Tree (AST) evaluation, presents the first systematic evaluation of SOTA LLMs such as GPT-4, and Claude-v1. We benchmark them for Accuracy and Hallucination. Our experiments demonstrate what most people "felt", GPT-4 hallucinates more than GPT-3.5 👀

1

7

34

Shishir Patil

@shishirpatil_

1 year

We have continued developing Gorilla: your go-to open-source API marketplace for LLMs 🦍Our colab has seen over 3k+ users in 3 days 🚀 A big thank you for your enthusiastic response 🫡 Gorilla is open source and will always be community driven. ⏲ Check out Gorilla in 60seconds:

Tianjun Zhang

@tianjun_zhang

1 year

📢It has been a thrilling 5 days since Gorilla release 🚀 Updates: + We released HF, TF and Torch Hub Gorilla zero-shot models + Opened up APIZoo for community contributions + 2k GitHub stars 🤩 and 780+ welcoming discord community 🎙️ Now, to answer the most pressing question

0

2

17

1

3

27

Shishir Patil

@shishirpatil_

9 days

Check out @AIatMeta 's post on RAFT for better in-domain RAG. Fun-fact, you can access it through: Meta and Microsoft: Divided by shareholders, united by Berkeley 😉

RAFT: Sailing Llama towards better domain-specific RAG

Retrieval-Augmented Fine-Tuning (RAFT) combines the benefits of Retrieval-Augmented Generation and Supervised Fine-Tuning for better domain adaptation.

ai.meta.com

2

5

58

Shishir Patil

@shishirpatil_

1 year

Gorilla’s retriever–aware training enables it to react to test time changes in the APIs. Gorilla is able to respond to model upgrades and changes in model registry at test-time. More information in our paper:

1

5

24

Shishir Patil

@shishirpatil_

11 months

🦍Week 3 🚀 📢 Introducing Gorilla-7b-hf-delta-v1, a major update turning user queries into insightful code suggestions! 👋Thrilled to rank #2 on Hacker News again! A hearty welcome to those who found us there. 🤝We're easing API discovery by transforming simple user queries into

Tianjun Zhang

@tianjun_zhang

11 months

📢How can Gorilla generate meaningful code snippets? This has been one of the first asks from the community 🤝 Today we have a major release: gorilla-7b-hf-delta-v1, a new model that gives code suggestions based on the query 🚀 Give it a try and let us know what you think! Check

2

0

10

0

6

24

Shishir Patil

@shishirpatil_

8 months

Thoroughly enjoyed this webinar with @jerryjliu0 from @llama_index and @jobergum ! Check out some key takeaways on integrating LLMs with Retrievers 🦙

Jerry Liu

@jerryjliu0

9 months

Here are six amazing insights from @jobergum and @shishirpatil_ on how to effectively use finetuning to optimize your LLM apps over your data: 1️⃣ Fine-tuning is actually remarkably effective at internalizing knowledge: retrieval algorithms in comparison can be inaccurate.

4

71

293

0

5

23

Shishir Patil

@shishirpatil_

21 days

Models are increasingly diverging in their areas of focus! This is exciting as we see a fragmentation in the use of function calling capabilities! 🤔The ability of a model to refuse to present an answer continues to remain challenging!!

0

5

22

Shishir Patil

@shishirpatil_

9 months

Honored to share the stage with luminaries at the @SimonsInstitute LLM workshop last week. In my talk, I delved into how Gorilla 🦍 adapts to imprecise retrievers and introduced a novel methodology to measure hallucination in LLMs. Watch the session here:

Short Talks

Nayoung Lee, Shishir Patil, Eric Wallacehttps://simons.berkeley.edu/talks/2023-08-18-0Large Language Models and Transformers

www.youtube.com

1

2

21

Shishir Patil

@shishirpatil_

10 months

We're thrilled to announce that our hosted Gorilla models have successfully processed over👏50,000 👏 user 👏 requests 🙇‍♂️ We're incredibly grateful for your overwhelming response and this has given us immense confidence to tear the initial stable releases on Github: 🦍Gorilla

Tianjun Zhang

@tianjun_zhang

10 months

Efficient Information retrievers are the solution to equip language models with the most up-to-date knowledge. 🚀 📢Releasing Gorilla+Retrievers to help keep APIs updated! We provide support for BM25 and GPT based retrievers in our GitHub: 🦍 Gorilla v0.0.1:

3

1

20

0

1

20

Shishir Patil

@shishirpatil_

9 months

Check out the @weaviate_io paper summary on #GorillaLLM 🦍 @CShorten30 does a phenomenal job on diving deep into the core research and presents lots of useful advise to those working on retrievers, LLMs, or APIs 🤩

Connor Shorten

@CShorten30

9 months

I am SUPER excited to present a paper summary video of Gorilla: Large Language Models Connected to Massive APIs! 🦍🛠️ API instruction following, Self-Instruct, Retrieval-Aware Training, and more! One of the most exciting papers I've seen recently! 🤯🚀

5

23

84

1

4

19

Shishir Patil

@shishirpatil_

2 years

Moving data between cloud object stores is a growing phenomenon. Our work presents the first solution in optimizing data movement across AWS (S3 buckets), Azure (Blobs) and Google Cloud (Storage).

Paras Jain

@_parasj

2 years

Releasing Skyplane, a new open-source tool to move huge datasets between clouds. Skyplane is: 1. 🔥 Blazing fast (110x faster) 2. 🤑 Cheap (4x cheaper) 3. 🌐 Universal (AWS, Azure and GCP) Read more: 1/

8

57

259

0

2

17

Shishir Patil

@shishirpatil_

9 months

I'm always amazed by the energy @CShorten30 injects into his podcast! Had the privilege to be a part of it 🤩 Don't miss the latest episode of Weaviate 🤝 Gorilla podcast!

Shishir Patil and Tianjun Zhang on Gorilla - Weaviate Podcast #64!

Hey everyone! Thank you so much for watching the 64th Weaviate Podcast with Shishir Patil and Tianjun Zhang, co-authors of Gorilla: Large Language Models Con...

www.youtube.com

Connor Shorten

@CShorten30

9 months

Beyond excited to publish our newest Weaviate Podcast with @shishirpatil_ and @tianjun_zhang , co-authors of the Gorilla LLMs!! 🦍🛠️🎉 Loved this discussion on all things Gorilla, from the APIZoo to Self-Instruct, Retrieval-Aware Training, and more! 📚

2

14

38

1

5

17

Shishir Patil

@shishirpatil_

1 year

I don't know how @arankomatsuzaki does it 🙇‍♂️ but our advisor @profjoeyg saw his tweet before he saw our arXiv notification!

Aran Komatsuzaki

@arankomatsuzaki

1 year

Gorilla: Large Language Model Connected with Massive APIs Releases Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls. proj: abs:

18

194

746

0

17

Shishir Patil

@shishirpatil_

10 months

@AlphaSignalAI Thanks for featuring our work! Gorilla 🦍 is an open source project from UC Berkeley with some exciting new releases planned! Stay tuned! 😉

0

1

16

Shishir Patil

@shishirpatil_

2 months

In today's updates to the Berkeley Function Calling leaderboard: 📊Enhanced Leaderboard with Additional Models and Summary Table: @MistralAI -large-2402, @GoogleAI Gemini 1.0 Pro, and Gemma now included. 🤖 Gradio for Interactive Exploration! Includes function calling demos, and

0

5

13

Shishir Patil

@shishirpatil_

27 days

Check out how good is Llama 3 on tool calling 👀 Thorough work by @RickLamers on the Berkeley Tool Calling Leaderboard!

Rick Lamers

@RickLamers

28 days

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!

21

39

305

0

2

14

Shishir Patil

@shishirpatil_

8 months

Delighting to see Gorilla's newest infant 🦍 Weaviate Gorilla 😊Checkout @CShorten30 's blog and video on how you can use LLMs to invoke GraphQL APIs 🛠️🚀 Blog: Youtube:

Weaviate Gorilla Part 1: GraphQL APIs!

Hey everyone! Thank you so much for checking out the 1st episode of our Weaviate Gorilla project! We trained LlaMA 7B to write Weaviate queries!Please check ...

www.youtube.com

Connor Shorten

@CShorten30

8 months

We trained LlaMA 7B to use Weaviate!! 🦍🛠️ Presenting... Weaviate Gorilla Part 1: GraphQL! 🎉 Blog Post: YouTube: 🧵 With some more details 👇

16

76

244

1

4

14

Shishir Patil

@shishirpatil_

9 months

Fine-tune smaller models or switch to fine-tuning 3.5 from #OpenAI ? Exciting experiment by @morgymcg on the #GorillaLLM dataset. Watch along and track the progress in real time 🤩

Morgan McGuire

@morgymcg

9 months

Put together a quick colab to fine-tune @OpenAI ChatGPT-3.5 on the huggingface api code from the gorilla dataset Idea being to see if something like this can help improve ChatGPT-3.5's use of tools and mimic GPT-4's `functions` capability

5

9

43

0

2

13

Shishir Patil

@shishirpatil_

1 month

Thanks for sharing our work @arankomatsuzaki 🫡

Aran Komatsuzaki

@arankomatsuzaki

1 month

GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications Presents a runtime for LLMs with an intuitive undo and damage confinement abstractions, enabling the safer deployment of LLM agents in practice repo: abs:

1

23

84

0

2

13

Shishir Patil

@shishirpatil_

3 months

Using LLMs to call functions is 🚀🚀🚀 When we released OpenFunctions-v1 the community loved the models 🙏 but we quickly realized evaluation needed attention 👀 It took a while, but we are delighted to share the Berkeley Function-Calling Leaderboard. + Abstract Syntax Tree (AST)

1

12

Shishir Patil

@shishirpatil_

8 months

Agreed!! Love the graphic 🔥🔥🔥 Weaviate Gorilla is now out! Check it out 🚀🦍

Connor Shorten

@CShorten30

8 months

Preview of our initial Weaviate Gorilla release, GPT-4 is amazing at generating synthetic Weaviate database schemas! 🦍🦍🦍 Love the way this slide turned out haha, all sorts of applications for Weaviate! Just ask an LLM! 🤗🍱🐕💊🍿📱🏀🎶🎮👕⛈️🌍🎻🚗

3

15

57

0

3

11

Shishir Patil

@shishirpatil_

10 months

🦍 in AI Business’s top 12 models - Read more at

12 Language Models You Need to Know

The future of natural language processing: Next-generation AI models to power enterprise use cases

aibusiness.com

Joey Gonzalez

@profjoeyg

10 months

I am excited to announce that two of the LLMs from my group (Gorilla and Vicuna) are on AI Business’s top 12 models. Congrats @shishirpatil_ , @tianjun_zhang , @xinw_ai , and the @lmsysorg team. We are looking forward to working with @Meta on Llama-v2 versions.

2

7

51

0

9

Shishir Patil

@shishirpatil_

11 months

@altryne Try it out :)

GitHub - gorilla-llm/gorilla-cli: LLMs for your CLI

LLMs for your CLI. Contribute to gorilla-llm/gorilla-cli development by creating an account on GitHub.

github.com

0

4

9

Shishir Patil

@shishirpatil_

6 months

🫡 The stellar team behind this @fanjia_yan @AbecidAdam @tianjun_zhang and yours truly, shepherded incredibly by Ion Stoica, and @profjoeyg 🙏

2

0

9

Shishir Patil

@shishirpatil_

8 months

🦍 #GorillaLLM 🤝 @weaviate_io 🤝 @1littlecoder 🫡🔥🙏

Connor Shorten

@CShorten30

8 months

Super happy that Weaviate Gorilla was featured in @1littlecoder 's AI Updates series!! Thank you so much and massive kudos on the series - really impressive diversity! One of the best AI / ML news shows out! 🔥🙏

5

10

35

0

1

8

Shishir Patil

@shishirpatil_

1 month

🌐 Pioneering a future where LLMs empower microservices & apps, evolving from mere data retrievers 🧵to autonomous decision-makers within our digital world 🧙 Wondering about the safety and correctness of these interactions🤔? Our latest vision paper explores these questions,

1

9

Shishir Patil

@shishirpatil_

20 days

While one can further improve the throughput with optimizations, and of-course costs vary with the contracts and vintage of GPUs, that is besides the point. With cost and latency, our goal is to identify what the magnitude of costs and latency looks like, and understand the

2

8

Shishir Patil

@shishirpatil_

1 year

🤩 Shoutout to @omarsar0 who did a much better job explaining our paper on Twitter than we ever could 🙏

elvis

@omarsar0

1 year

Finetuning LLMs to call APIs Present Gorilla, a finetuned LLaMA-based model that surpasses GPT-4 on writing API calls. This capability can help identify the right API, boosting the ability of LLMs to interact with external tools to complete specific tasks. Huge potential for

14

208

880

1

0

7

Shishir Patil

@shishirpatil_

2 months

@simonw @AnthropicAI @DbrxMosaicAI Yeah - spot on! And we also describe the methodology and eval-metrics here:

1

0

8

Shishir Patil

@shishirpatil_

23 days

💯

martin_casado

@martin_casado

24 days

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

10

9

133

0

1

7

Shishir Patil

@shishirpatil_

8 months

@CShorten30 Putting the "W" back in @weaviate_io 🤩 Congratulations @CShorten30 and @philipvollet Exciting days 🚀🚀🚀

1

6

Shishir Patil

@shishirpatil_

3 months

Joint work with @UCBerkeley 's finest undergrads @charlie_jcj02 , @fanjia_yan , @HuanzhiMao and project co-led by @tianjun_zhang , Ion Stoica, and @profjoeyg 🫡

1

0

6

Shishir Patil

@shishirpatil_

3 months

🎁In OpenFunctions-v2, we natively train the model to support parallel functions (generate multiple functions at a time) and multiple functions (select one or more functions). Java/REST/Python APIs are also supported for the first time with extended data types📷 Looking forward

1

6

Shishir Patil

@shishirpatil_

7 months

🔥

Sai Vemprala

@saihv

7 months

Introducing GRID: the General Robot Intelligence Development platform, designed for prototyping smart and safe robots rapidly using foundation models, LLMs, and simulation. Paper: Try now: GitHub: 🧵👇(1/N)

18

188

875

0

5

Shishir Patil

@shishirpatil_

2 years

Picking the right loss functions for adaptation on the fly! Excited for @zicokolter talk on @goyalsachin007 work #ICML2022

Sachin Goyal @ ICLR ‘24 🏰

@goyalsachin007

2 years

How do you find the "right" loss for test-time adaptation to distribution shifts? Turns out we can use convex conjugates! New paper📢 with @Eric_jie_thu , Aditi Raghunathan, @zicokolter . Test-Time Adaptation via Conjugate Pseudo-labels

4

24

112

0

1

5

Shishir Patil

@shishirpatil_

10 months

@marktenenholtz Thanks for featuring our work @marktenenholtz Appreciate it 🙇‍♂️ 🦍

0

3

Shishir Patil

@shishirpatil_

1 month

🤩 Looking good 🦍👌😂

Alex Immerman

@aleximm

1 month

@TaliaGold @skupor @a16z @DavidGeorge83 @sarahdingwang @jamiedsully @stacydamico @justin_kahl @santiago__rdz @steph_zhang @BobSwan @CarolineGoggs @TugceErten2022 credit to @shishirpatil_ @tianjun_zhang for the model, @lauten for the idea, and @steph_zhang for the costume

0

7

0

4

Shishir Patil

@shishirpatil_

2 years

Special thanks to @jainprateek_ , @smolix , and @petewarden for the intense brainstorming sessions 🙂 @drothkid , @charlespacker for ✍️ suggestions.

0

4

Shishir Patil

@shishirpatil_

11 months

@sunilmallya Thanks for your interest @sunilmallya Yes, indeed! We will open-source the dataset for the newer APIs as well!

1

4

Shishir Patil

@shishirpatil_

10 months

@CShorten30 @tianjun_zhang @weaviate_io Absolutely @CShorten30 ! Would love to make Gorilla 🤝 @weaviate_io happen 🤩

2

0

4

Shishir Patil

@shishirpatil_

5 months

@rajko_rad @a16z @arthurmensch @GuillaumeLample @tlacroix6 @MistralAI @AnjneyMidha @BornsteinMatt Congratulations @rajko_rad 🔥

0

1

Shishir Patil

@shishirpatil_

8 months

Had a great chat with @chsrbrts on #GorillaLLM How often do you think hyperscalers change their APIs? Spoiler: More than once a day!!! Check out the blog to learn more 🦍🦍🦍

Chase Roberts

@chsrbrts

8 months

We interview @shishirpatil_ on Episode #5 of Neural Notes about Gorilla, an LLM that generates API calls.🦍 Why does this matter? LLMs are well-suited for code generation bc the task is forgiving since there are multiple ways to write a function, but they struggle with API code

1

5

13

0

4

Shishir Patil

@shishirpatil_

2 years

Exciting to see the tides shift. 'ML sensors' decouples the abstraction between the ML-enabled-sensors and and the rest of the system.

Pete Warden

@petewarden

2 years

I'm finally able to talk about what I've been up to for the last six months!

18

22

209

0

3

Shishir Patil

@shishirpatil_

9 months

@CShorten30 @tianjun_zhang Note to self: Need to set-up good lighting 🙈😀

1

0

2

Shishir Patil

@shishirpatil_

1 month

@jiayq Agree on (1) and (2). Although for (3), from the set of our users, we actually see a healthy number of scenarios where you are choosing between a handful of functions. Especially in enterprise use-cases, it's either choose A/B/C or default D (usually support, doc q-a, etc)..

1

3

Shishir Patil

@shishirpatil_

3 months

@intrstllrninja Thanks for your kind words @intrstllrninja Eval Code: Eval Dataset: Let us know if you run into any issues, or as with any open-source feel free to raise a PR!

gorilla-llm/Berkeley-Function-Calling-Leaderboard · Datasets at Hugging Face

huggingface.co

1

0

3

Shishir Patil

@shishirpatil_

2 years

Our framework, Private Optimal Energy Training (POET) takes a memory and a run-time budget as input. POET schedules nodes of the training graph to satisfy the constraints by exploiting integrated rematerialization and paging. POET's MILP formulation is provably energy-optimal!

1

0

3

Shishir Patil

@shishirpatil_

1 month

@Teknium1 @ivanfioravanti @Teknium1 it's added with PR This plot might be useful for understanding where different models shine! @ivanfioravanti depending on your use-case, your mileage may vary! Of-course let us know if you have any comments, suggestions, find bugs, or

2

0

3

Shishir Patil

@shishirpatil_

1 month

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 🗞️

Xiuyu Li

@xiuyu_l

1 month

Handling long context in LLMs is expensive, but can we cut the cost by learning them offline for a specific set/genre of documents? Introducing LLoCO, our new technique that learns documents offline through context compression and in-domain finetuning using LoRA, which archives

7

53

269

1

3

Shishir Patil

@shishirpatil_

16 days

@djfarrelly @inngest You may find this to be an useful tool:

1

0

2

Shishir Patil

@shishirpatil_

8 months

@_parasj Congratulations on the release Paras! 🔥

1

0

2

Shishir Patil

@shishirpatil_

10 months

@AustinNWharton @marktenenholtz Hey @AustinNWharton thanks for sharing your feedback! Gorilla CLI is fully open sourced, and commands are executed only with users explicit approval! Let us know if there is anything we can do that would make you feel more comfortable giving it a try!

0

2

Shishir Patil

@shishirpatil_

9 months

@ishaan_jaff Wow, that's a nice side-by-side comparison tool 🚀

0

2

Shishir Patil

@shishirpatil_

8 months

@1littlecoder @CShorten30 Yeah echo that - thanks for covering it @1littlecoder 🙏

1

0

2

Shishir Patil

@shishirpatil_

28 days

@JenniferHli Congratulations @JenniferHli and best wishes 🍾 😊

1

0

2

Shishir Patil

@shishirpatil_

10 months

@dav_ell @AlphaSignalAI Thanks for trying it and your kind words @dav_ell 🫡

2

0

2

Shishir Patil

@shishirpatil_

10 months

@dotey Hey @dotey 👋 We do have some metrics in the paper, but would love it if you gave it a try and have any feedback for us on how we can improve it! 🙂

0

2

Shishir Patil

@shishirpatil_

10 months

@simonw Loved to see the clean integration! This is another great modality to use gorilla right in your CLI!

0

Shishir Patil

@shishirpatil_

8 months

🦍

Omar Sanseviero

@osanseviero

9 months

Which are the best ML discord servers to join? So many 😱 How to keep up with all of them? Which ones am I missing? LAION Eleuther OS Shrunkworks AI (MoE project) Hugging Face CarperAI Open Assistant Harmonai (Dance Diffusion) Replicate Suno (bark, TTS) Stable Foundation Invoke

31

42

289

0

2

Shishir Patil

@shishirpatil_

2 years

With POET, we are the first to demonstrate training of memory-hungry SOTA ML models such as BERT and ResNets on smartphones and tiny ARM Cortex-M devices! 💪 With my wonderful collaborators @_parasj , @prabaldutta , Ion Stoica, and @mejoeyg at @berkeley_ai @ucbrise @Berkeley_EECS

1

0

2

Shishir Patil

@shishirpatil_

20 days

@AarushSah_ Few

0

1

Shishir Patil

@shishirpatil_

1 month

@jeankaddour Thanks @jeankaddour Appreciate it 🙏

0

1

Shishir Patil

@shishirpatil_

1 month

@andreasklinger Thanks @andreasklinger 🤣

0

1

Shishir Patil

@shishirpatil_

15 years

Looking out for followers

0

1

Shishir Patil

@shishirpatil_

2 months

@skypilot_org cyberpunk 2077 when? Congratulations 🎉

1

0

1

Shishir Patil

@shishirpatil_

3 months

@kihemaitien Thanks for bringing this to our attention, @kihemaitien . In the process of adding!

0

1

Shishir Patil

@shishirpatil_

2 years

Fine-tuning models on the edge satisfies privacy constraints and enables offline operation. However, limited memory on edge makes training memory-hungry deep learning models infeasible.

1

0

1

Shishir Patil

@shishirpatil_

3 months

@ibuildthecloud Excited to see how it goes @ibuildthecloud ! Let us know if you have any feedback on the leaderboard or the model.

0

1

Shishir Patil

@shishirpatil_

1 year

@nickarner Here's our work on training memory intensive models on smartphones and microcontrollers (ARM Cortex M4s)

0

1

Shishir Patil

@shishirpatil_

2 months

@realgmittal @ContextualAI Congratulations @realgmittal 🎉

0

1

Shishir Patil

@shishirpatil_

7 months

@lisabdunlap +1 Can confirm. Lisa has her way with matplotlib 🫡

0

1

Shishir Patil

@shishirpatil_

8 months

@conor_power23 @eternalroree *feature not bug 🤝

0

1

Shishir Patil

@shishirpatil_

9 months

@alexchaomander Was great chatting with you @alexchaomander Really appreciated the insightful questions!!

0

1

Shishir Patil

@shishirpatil_

2 years

@EugeneVinitsky Yeah, and you want to make sure you power them sufficiently. If you don't give them enough juice, they'll be severely under-clocked even in headless mode.

1

0

1

Shishir Patil

@shishirpatil_

4 years

@pschafhalter Multics. Does it ring a bell ?😉

1

0

1

Shishir Patil

@shishirpatil_

8 months

@CShorten30 The pleasure was mine, Connor!! Excited to see this partnership blossom ❤️ and great job on the release 🫡

1

0

1