@BerkeleySky Profile picture

UC Berkeley Sky

@BerkeleySky

Sky Computing - looking for the Berkeley Skydeck? They’re on the other side of Campus from us @SkyDeck_Cal.

Similar User
Woosuk Kwon photo

@woosuk_k

SkyPilot photo

@skypilot_org

Joey Gonzalez photo

@profjoeyg

Conor Power photo

@conor_power23

Dacheng Li photo

@DachengLi177

Suyash Gupta photo

@suyash_sg

Sam Kumar photo

@samkumar_cs

Lianmin Zheng photo

@lm_zheng

Sarah Wooders 👾 photo

@sarahwooders

Hao Zhang photo

@haozhangml

Zhanghao Wu photo

@Michaelvll1

Zongheng Yang photo

@zongheng_yang

Romil Bhardwaj photo

@bromil101

Lily Liu photo

@eqhylxx

Alvin Cheung photo

@alvinkcheung

UC Berkeley Sky Reposted

New short course: LLMs as Operating Systems: Agent Memory, created with @Letta_AI, and taught by its founders @charlespacker and @sarahwooders An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So,…


UC Berkeley Sky Reposted

📣 Announcing BFCL V3 - evaluating how LLMs handle multi-turn, and multi-step function calling! 🚀 For agentic systems, function calling is critical, but a model needs to do more than single-turn tasks. Can it manage multi-turn workflows, handle sequential functions, and adapt to…

Tweet Image 1

UC Berkeley Sky Reposted

🙏 Thank you @nvidia for sponsoring vLLM development. The DGX H200 machine is marvelous! We plan to use the machine for benchmarking and performance enhancement 🏎️.

Tweet Image 1

UC Berkeley Sky Reposted

📢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 &…


UC Berkeley Sky Reposted

Joint work from a super fun collaboration with @kingh0730 @minimario1729 @xu3kev @fanjia_yan @tianjun_zhang @sidawxyz Armando Solar-Lezama @koushik77 and Ion Stoica across UC Berkeley, MIT, and Cornell! Paper URL - arxiv.org/abs/2403.07974 Keep reading for the key takeaways!!


UC Berkeley Sky Reposted

🌀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:…

📢 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…

Tweet Image 1


UC Berkeley Sky Reposted

📢 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…

Tweet Image 1

UC Berkeley Sky Reposted

Announcing the 2nd Confidential Computing Summit June 5-9, 2024 in SF. Last year was a success with double the expected attendance & submissions! Submission for presentations is now open until Feb 29. Submit your exciting work! @confcompsummit confidentialcomputingsummmit.com

Tweet Image 1

UC Berkeley Sky Reposted

Berkeley Data Systems and Foundations team were a big presence at @cidrdb #cidr24 including two talks and two gong show wins. Happy to reunite with alumni and the godfather himself, Mike Stonebraker. Good times! @Berkeley_EECS @UCBerkeley @UCBEPIC @BerkeleySky

Tweet Image 1

UC Berkeley Sky Reposted

We are thrilled to introduce SGLang, our next-generation interface and runtime for LLM inference! It greatly improves the execution and programming efficiency of complex LLM programs by co-designing the front-end language and back-end runtime. On the backend, we propose…

Tweet Image 1

UC Berkeley Sky Reposted

Exciting Arena Leaderboard Updates! Six new models: - Tulu-2-DPO-70B and Yi-34B-Chat are the new SoTA open models - Mistral-based 7B models (OpenChat, OpenHermes-2.5, Starling-7B) are stronger than ever Big congrats to the OSS AI community! Learn more lmsys.org/blog/2023-12-0…

Tweet Image 1
Tweet Image 2

Check out the first-open source alternative for LLM function calling! #GorillaLLM

📢 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…

Tweet Image 1


Loading...

Something went wrong.


Something went wrong.