InTDS ArchivebyIda SilfverskiöldAdvanced Prompt Engineering: Chain of Thought (CoT)Comparing different techniques for reasoningDec 23, 202413Dec 23, 202413
InData Science CollectivebyIda SilfverskiöldEconomics of LLMs: Evaluations vs PricingLooking at which model to use for which taskFeb 2012Feb 2012
InTowards AIbyAlden Do RosarioDear IT Departments, Please Stop Trying To Build Your Own RAGIT departments convince themselves that building their own RAG-based chat is easy. It’s not. It’s a nightmare.Nov 12, 2024171Nov 12, 2024171
InData Science at MicrosoftbyShimin ZhangEvaluating LLM-based chatbots: A comprehensive guide to performance metricsBy Shimin Zhang, Yan Chen, Rui Hu, and Gorkem Ozer YilmazOct 31, 2024Oct 31, 2024
InTDS ArchivebyMurilo GustineliThe Art of Tokenization: Breaking Down Text for AIDemystifying NLP: From Text to EmbeddingsSep 26, 20243Sep 26, 20243
InThe Modern ScientistbyYule Wang, PhDA Complete Guide to LLMs-based Autonomous Agents (Part I):— — Chain of Thought, Plan and Solve/Execute, Self-Ask, ReAct, Reflexion, Self-Consistency, Tree of Thoughts and Graph of ThoughtsOct 9, 20238Oct 9, 20238
InTowards AIbyLouis-François BouchardThe Best RAG Stack to Date(exploring every component)Sep 14, 202417Sep 14, 202417
InCubedbyMichael WoodEliminating Hallucinations Lesson 1a: Source Code for Named Entity Filtering (NEF)Here is the code needed to implement production-ready Named Entity Filtering (NEF) discussed in Hallucination Elimination Lesson One.Sep 17, 20241Sep 17, 20241
InCubedbyMichael WoodEliminating Hallucinations Lesson 1: Named Entity Filtering (NEF)Named Entity FilteringSep 2, 202417Sep 2, 202417
InTDS ArchivebyBenjamin MarieQuantize Llama 3 8B with Bitsandbytes to Preserve Its AccuracyLlama 2 vs. Llama 3 vs. Mistral 7B, quantized with GPTQ and BitsandbytesMay 27, 2024May 27, 2024
InSnowflake Builders Blog: Data Engineers, App Developers, AI/ML, & Data SciencebyChase GintherResponsible AI on Snowflake: Snowflake Cortex LLM’s + Snowpark Container Services + Snowflake…Enterprises are eager to adopt GenAI at scale but struggle with how to govern it in the enterprise. NVIDIA & Snowflake have solutions..May 12, 2024May 12, 2024
InSnowflake Builders Blog: Data Engineers, App Developers, AI/ML, & Data SciencebyMurali GandhirajanInteract with LLM to search and uncover insights from medical transcript documentsRetrieval Augmented Generation (RAG) Using Snowflake Cortex LLMMay 6, 20243May 6, 20243
InTDS ArchivebyJarek Grygolec, Ph.D.Evaluate RAGs Rigorously or PerishUse RAGAs framework with hyperparameter optimisation to boost the quality of your RAG system.Apr 26, 2024Apr 26, 2024
Michael GorkowCustom Embedding Models from Hugging Face in SnowflakeUnlocking Multilingual RAG Capabilities in Snowflake with Custom Hugging Face ModelsApr 14, 20241Apr 14, 20241
InTDS ArchivebyBenjamin MarieMarlin: Nearly Ideal Inference Speed for 4-bit Large Language ModelsUp to 4x faster than inference with fp16 parametersMar 30, 20242Mar 30, 20242
InData Science at MicrosoftbyJane HuangEvaluating LLM systems: Metrics, challenges, and best practicesA detailed consideration of approaches to evaluation and selectionMar 5, 202421Mar 5, 202421
InSnowflake Builders Blog: Data Engineers, App Developers, AI/ML, & Data SciencebyCarlos CarreroAsking Questions to Your Own Documents with Snowflake CortexUnderstanding and analyzing unstructured data with the help of Large Language Models (LLMs) has become a very hot topic. Almost every…Jan 11, 20243Jan 11, 20243
Tom ChristianRAG Made Simple with Snowflake CortexEnd to end RAG within a single data platform? Cortex makes things simple.Jan 4, 20243Jan 4, 20243
InTDS ArchivebyAhmed BesbesHow To Build an LLM-Powered App To Chat with PapersWithCodeKeep up with the latest ML researchFeb 1, 20249Feb 1, 20249