Peter Wang

🚀 Looking to streamline fine-tuning for models like Llama 3, Mistral, and Mixtral? Our latest blog shows how Anyscale simplifies LLMs fine-tuning with Ray: 🔑 Key takeaways: • Scalable fine-tuning with LLM-Forge • Model Deployment with RayLLM Read more: https://lnkd.in/gQwD4A2U

35

【Script-Based GPU-Ready ELM Development for Continuous Code Integration】 Full article: https://lnkd.in/gFM7gFdQ (Authored by Peter Schwartz, et al., from Oak Ridge National Laboratory, Environmental Sciences Division (USA), etc.) The E3SM Land Model (#ELM) is an integral part of the Energy Exascale Earth System Model (E3SM) framework, simulating the interactions between terrestrial land surfaces and other Earth system components. ELM has been instrumental in understanding hydrologic cycles, biogeophysics, and dynamics of terrestrial ecosystems. To facilitate the automatic porting of individual ELM modules, the researchers have developed a #software tool named SPEL. This work presents a SPEL extension that leverages the version control system (e.g., Git) to autonomous code generation and demonstrate its application to #continuous_code_integration and development of the ELM software system.  

2

🧠 What’s a Semantic Cache in RAG? Here’s What We’ve Learned Semantic cache is a time and cost saving method for Retrieval Augmented Generation (RAG). Instead of always running a full vector search, a semantic cache stores embeddings of frequently asked queries and their responses. This speeds up your RAG system by skipping redundant searches for similar queries. How do you implement it? Step 1: Store history of answered questions, their embeddings and the LLM response in a semantic cache table. Step 2: When a new query comes in, compare it against the cache table using vector similarity. Step 3: If there’s a match with score over a certain threshold, serve the cached response. If not, run a fresh retrieval and add it to the cache. Now, let’s talk vector search methods: 1️⃣ Cosine Similarity: Measures angle between vectors, works well for normalized data. 2️⃣ Euclidean Distance: Measures straight-line distance but can be skewed by vector magnitude. 3️⃣ Dot Product: Our favorite—it factors in vector size and performs best for our use cases. Want to see how semantic caching powers a RAG system in real life? Check out our demo at https://lnkd.in/g2jFuHTT. 🚀

2

Are you interested in vector search, indexing, or database efficiency? Then you won't want to miss this talk by Etienne Dilocker from Weaviate at Carnegie Mellon University's Database Group with Andy Pavlo! Etienne breaks down key challenges and innovations that are powering the future of search: ✨ Bit-Sliced Indexing - tackling complex range queries like price filters with innovative indexing. ✨ BM25 Hybrid Search - combining keyword and vector search to handle nuanced queries. ✨ Graph-Based Indexing (HNSW) - optimizing for high update rates and recalls without latency drops. ✨ Overcoming the Minority Filter Problem - enhancing search relevance through in-place filtering, based on the ACORN paper. ✨ Weaviate's Roadmap - performance, enterprise readiness, and pioneering "Recommendations as a Service." Check out the full talk for an in-depth look at how Weaviate is setting new standards in search technology: https://lnkd.in/gavAZRrn

33

2 Comments

Paco Nathan has a new blog on O'Reilly called: "Unbundling the Graph in GraphRAG." What is GraphRAG? How can it help reduce hallucinations? How does entity resolution help LLMs? https://hubs.li/Q02Zdrhp0 #EntityResolution #GraphRAG #LLM #EntityResolution #ERKG #EntityResolvedKnowledgeGraph #EntityResolvedKnowledgeGraphs #KnowledgeGraph #KnowledgeGraphs #GraphTechnology #GraphAnalytics

54

2 Comments

The NeurIPS Navigator: A Behind the Scenes Look, Powered by Cerebras Inference ⚡ How do you create RAG app that turns 4,500+ research papers from the 2024 NeurIPS Conference? Dive into how we processed PDFs, created embedding chunks and stored it in on Postgres in a performant way. Created by our Fellow Isaac Tai Read more here: https://bit.ly/4fUOf8m

59

2 Comments

Great post by Vu Trinh on Apache Hudi's motivations (how it started at Uber) and the internals. Vu discusses Hudi's incremental processing approach, metadata structure, and table types. The blog also highlights Hudi's unique indexing feature, emphasizing Hudi's ability to handle large-scale data efficiently. Check out the link for a detailed read 👇 https://lnkd.in/dhCmM6v2 #dataengineering #softwareengineering

75

2 Comments

Category of the week: Procedural Languages Select extension: PL/R 💭 It's not uncommon for analysts and researchers to leverage an IDE (Integrated Development Environment) for incidental statistical or aggregate processing. This tends to involve tremendous manual effort, and is difficult to scale. 💡 PL/R grants the user the power of the R programming language, which allows for example, statistical analysis on the data where it lives; this workflow can be further supported by materialized views, for example. Source: https://lnkd.in/gBrZ7esP Link: https://lnkd.in/er_G7dbY 🧰 Check PL/R out and similar extensions within the Procedural Languages category on Trunk; a Postgres extension registry! https://lnkd.in/g7pvNg2c 📊 Tembo is powered by Trunk's ever-growing collection of Postgres extensions, and Tembo users have the freedom to choose. Try out this extension and more on Tembo Cloud, for free! https://lnkd.in/gDQjj8ur

11

Exciting New Methods for Efficient Fine-Tuning of LLMs using PEFT (BOFT, VeRA, and PiSSA) via #TowardsAI → https://bit.ly/3xarDQv

3

💡 GPU? Lazy eval? No problem! 💻 Write dataframe code that works beautifully across pandas, Polars, cuDF & more with Narwhals. 🔥 Check out our in-depth blog, by Marco Gorelli on making data science more interoperable: https://lnkd.in/dedkSPPy #Polars #DataFrame #Pandas #Narwhals

14

🔍 Curious about optimizer performance? Benjamin Marie's latest article delves into a comparative analysis of AdamW-32bit, its 8-bit variant, and paged AdamW optimizers. Discover their effects on memory consumption, learning curves, and training time. #MachineLearning #Programming

13

#Dapr 1.15 is almost here! Check out what's coming down the pike, like streaming subscriptions with #Python, production-ready workflows, and Conversation API for interfacing with LLMs. 🎥 Watch the webinar recording for demos, Q&A, and presentations from the minds behind this big release: https://bit.ly/3Dg9ROv

9

1 Comment

A great read on the performance and financials of LLM fine-tuning. Really hoping the outcome is a tool that helps overcome the biggest elephant in the room, Mr. Cost! #llm #finetuning #finance #computaioncosts

2

1 Comment

Here's a snippet demonstrating how you can use Mirascope to make your LLMs take conditional actions based on the classification of an input. Check out the full example at https://lnkd.in/eV8wE5C2

11

2 Comments

Introducing a new approach to graph-enabled RAG. LazyGraphRAG needs no prior summarization of source data, avoiding prohibitive up-front indexing costs. It’s inherently scalable in cost and quality across multiple methods and search mechanisms: https://lnkd.in/eMsfeiey

513

12 Comments