Jaeho Shin

Large Language Models (#LLMs) are evolving rapidly, and the demand for running them at scale is skyrocketing. #Ollama is stepping up to meet this need with its official container image on Docker Hub, excelling in local #deployments. However, there’s a catch for containerized environments: downloading #models requires the ollama serve command to be running within the #container. This extra step complicates automated deployments via #CI #CD #pipelines, making seamless model access challenging. To take your #model to production, it needs to be #container-ready—a feature Ollama has yet to fully support. The gap in #AIOps for smooth deployments gets blurred with the inference services available as an easy way to take it to production. Goal is to overcome obstacles and deliver solutions 😉 so here is to get you started on having your (O)#llama #production ready in a private #deployment from your #local to #cloud all in #oneshot . Enjoy Medium: https://lnkd.in/g9jqBQ8d dev.to: https://lnkd.in/gi_gGwam #AI #LLM #Ollama #llama3 #phi3 #mistral #S6overlay #AIOps #CI #CD #oneshot #container #docker #podmanEnjoy

11

A data-driven approach to driving wound healing outcomes Marcella Gomez, University of California, Santa Cruz https://lnkd.in/gAkWZYJT Meet: https://lnkd.in/g4AAWkcK YouTube Stream: https://lnkd.in/gwtqaTmf Talk details: https://lnkd.in/gWn3B3cU Subscribe for talk announcements: https://lnkd.in/g5ciuNuX Abstract: Precision medicine requires an ability to predict the response of an individual to a prescribed treatment regimen a priori. Thus, advancement in the field is challenged by a lack of predictive models and, arguably, a lack of time-series information for a highly dynamic system. Here, we discuss work in wound healing, for accelerating wound closure. We argue that timing of treatments is as critical to consider as the choice of drug or therapy. Due to system size and complexity, data-driven methods need to be explored to develop multi-dimensional quantifiable indicators tracking systemic changes. In this work I discuss how bioelectronic devices enhanced with deep learning can help facilitate real-time sensing and actuation for automated decisions in treatment for wound healing and preliminary work in transcriptomic based classification of wound states. Bio: Marcella M. Gomez is an associate professor at UC Santa Cruz in the department of Applied Mathematics and Associate Dean for Diversity, Equity, and Inclusion for Baskin Engineering. She received her PhD from Caltech in 2015 and a B.S. from UC Berkeley in 2009; both degrees in Mechanical Engineering. Her research interests are in the broad field of bio-control leveraging methods in machine learning and control theory. Applications range from controlling single-cell response to driving complex systems such as wound healing. #modeling #simulation #medicine #healing #trauma #predictivemodeling #datascience #data #woundhealing #biology #bioengineering #systemanalysis #sensing #omics

3

Want a preview of what I'm going to be talking about in my keynote for RubyConf? You can catch a glimpse of it here!

10

LLMs have become more capable with better training and data. But they haven’t figured out how to “think” through problems at test-time. The latest research from Scale finds that simply scaling inference compute–meaning, giving models more time or attempts to solve a problem–is not effective because the attempts are not diverse enough from each other. 👉 Enter PlanSearch, a novel method for code generation that searches over high-level "plans" in natural language to encourage response diversity. PlanSearch enables the model to “think” through various strategies before generating code, making it more likely to solve the problem correctly. The Scale team tested PlanSearch on major coding benchmarks (HumanEval+, MBPP+, and LiveCodeBench) and found it consistently outperforms baselines, particularly in extended search scenarios. Overall performance improves by over 16% on LiveCodeBench from 60.6% to 77%. Here’s how it works: ✅ PlanSearch first generates high-level strategies, or "plans," in natural language before proceeding to code generation. ✅ These plans are then further broken down into structured observations and solution sketches, allowing for a wider exploration of possible solutions. This increases diversity, reducing the chance of the model recycling similar ideas. ✅ These plans are then combined before settling on the final idea and implementing the solution in code. Enabling LLMs to reason more deeply at inference time via search is one of the most exciting directions in AI right now. When PlanSearch is paired with filtering techniques—such as submitting only solutions that pass initial tests—we can get better results overall and achieve the top score of 77% with only 10 submission attempts. Big thanks to all collaborators on this paper including: Evan Wang, Hugh Zhang, Federico Cassano, Catherine Wu, Yunfeng Bai, William Song, Vaskar Nath, Ziwen H., Sean Hendryx, Summer Yue 👉 Read the full paper here: arxiv.org/abs/2409.03733

179

2 Comments

Elasticsearch open inference API adds native chunking support for @huggingface models, enabling developers to focus on building #GenAI applications without the burden of writing custom chunking logic. Dive into this blog to learn more: https://t.co/8IHgAykN70

2

Insightful how multi-agent AI can provide a better solution to many problems.

1

Anthropic's research on mapping concepts within LLMs https://lnkd.in/gmzW7W8Z offers a fascinating glimpse into how large language models represent the world. This advancement paves the way for better control and utilization of LLMs within the enterprise. #ResponsibleAI #MachineLearning #LargeLanguageModels #NLP

13

sharpening writing skill is one of killer skill!

2

Check out the latest in our "Debuggability" blog series! This blog is authored by Kevin Downey Jason Johl and me and talks about how we built a Debuggability Paved Road at Intuit using Ephemeral Containers and Argo Workflows. We'd love to hear your thoughts on the topic. Also, what tools do you build as-a-platform to help debug service, compute and network issues in Kubernetes at scale? #intuit #kubernetes #debug

22

Many of these techniques were completely new to me, and I foresee them being very useful: https://red.ht/4bBblya #ML #DL #NN #oss #opensource

4

Semantic-IDs has become our stepping stone connecting LLMs and recsys. Check out this paper to learn how it is also used to transform id representations in large embedding models.

156

1 Comment

Event Graph Walker - the new algorithm for collaborative text editing .. performs better than Operational Transformation or CRDTs .. https://lnkd.in/giZnAaJN When two users concurrently perform 𝑛 operations each, Eg-walker can merge them at a cost of 𝑂 (𝑛 log 𝑛), much faster than OT’s cost of 𝑂 (𝑛^2) or worse.

17

Happy Prompting...I mean Happy Halloween This video gets a bit more technical and discusses what you can do to move beyond basic RAG architectures. We discuss using multiple data stores, some uses of reranking, and touch briefly on techniques like hypothetical questions, metadata tagging, and other ways you can improve the results from your RAG application. Let me know what you think. And pass on any ideas or requests for future episodes. We're keeping a backlog of what to cover next. https://lnkd.in/gJhrpgSd

15

Test time training on LLMs to improve the accuracy of answers: https://lnkd.in/gWYeDFBu

1

Our latest release brings a number of updates that help you build generative AI (GenAI) applications, improve performance for core search and related workloads, and advance the way your teams work together with significant ease-of-use updates for OpenSearch Dashboards. #opensource #opensearch #genai #search #opensearchfoundation

31

https://lnkd.in/gcJsEKrG Q. What happens when #neural #networks are applied to fields like #Physics? A. In short, a Nobel Prize. More broadly, neural networks, built on the laureates' foundational work, have wide-ranging applications across science, technology, and various industries. They excel at tasks like pattern recognition, classification, and data generation. #Physics #AI #HVSays

13

1 Comment

When you need to play with your data in Gen Ai, you need RAG and Chunking is one of the main component in the RAG framework while consuming or processing your data. Excellent post below describing how in different ways chunking in RAG can be implemented..

23

1 Comment

LLMs: A Compass for Complex Information When working with large language models (LLMs), it’s clear that while they may not always help us hit the nail squarely on the head, they serve as a compass that points us in the right direction. LLMs are powerful tools for identifying patterns, performing semantic matching, and offering meaningful insights from vast amounts of data. While LLMs may only sometimes deliver perfect accuracy, they play a crucial role in helping us comprehend complex information quickly. They provide a solid foundation for decision-making and deeper exploration. Combining these AI-driven insights with human expertise creates a powerful partnership that leads to more informed and efficient outcomes. The takeaway: LLMs may not be precise hammers, but they’re invaluable compasses, guiding us toward more intelligent solutions. #AI #LLM #Innovation #MachineLearning #DataScience #DigitalTransformation #AIFuture

15

2 Comments