Gabi Dobocanblog.telepat.io路Nov 20, 2024Small Language Models: The Unsung Heroes of AI EfficiencyDigital landscapes are seeing a seismic shift towards language models that can process, learn, and perform tasks akin to human cognition. While large language models (LLMs) like GPT-3 have captivated attention, small language models (SLMs) are quietl...domain-specific knowledge
Pablo Salvador Lopezpabloaicorner.hashnode.dev路Aug 24, 2024Building an Effective Enterprise LLM/SLM Evaluation Framework: Key Strategies and ToolsStruggling to figure out how to evaluate and benchmark your GenAI apps? This article gives you an easy-to-follow guide for bulk evaluation and benchmarking of your GenAI applications. It talks about why a continuous evaluation framework is important,...420 readsGenAI in Production 馃promptflow
Pablo Salvador Lopezpabloaicorner.hashnode.dev路Aug 15, 2024Modernize Your Document Management with Azure AI and Generative AI: Advance OCR, Intelligent Tagging, and NERIs your company still manually processing millions of documents, classifying them by hand, or using outdated, inaccurate scripts to extract important information? Or perhaps you are deep into your GenAI efforts and have built advanced knowledge bases...1 like路377 readsAI That Matters馃専Azure AI document Intelligence
Kaushal Powarwrittenbykaushal.hashnode.dev路Jan 10, 2024Phi-2 has an MIT license now! Why not perform RAG using it?Yesterday I read a few posts about Microsoft Phi-2 LLM's license changed to MIT. What so fuss around it though? The old license was like "You are allowed to conduct testing locally; however, for production purposes, it is essential to execute the app...457 readsLLMphi2
