PinnedPublished inAI Advances4 Compression Techniques for Language ModelsCan you make LLMs smaller without sacrificing performance?Sep 26, 2024A response icon5Sep 26, 2024A response icon5
PinnedPublished inILLUMINATIONHow a Startup Can Avoid Death by Regulation3 books about lobbying for startups and NGOsJun 25, 2024A response icon9Jun 25, 2024A response icon9
PinnedPublished inPredictFacilitating Radiology and Healthcare with Medical AIhow far are we with Clinical Large Language Models with Med-GeminiMay 31, 2024A response icon4May 31, 2024A response icon4
PinnedPublished inILLUMINATIONThe 10 startups working on brain imaging to keep an eyeNeuroimaging from research to companyDec 16, 2022A response icon6Dec 16, 2022A response icon6
PinnedPublished inLevel Up CodingSimulating Chemical Reactions with Quantum Computing101 quantum chemistry, how to startApr 6, 2021A response icon2Apr 6, 2021A response icon2
Published inData Science CollectiveOpenLLM 101: How to Deploy LLMs with a Real API, Not Just a ToySome time ago, we were all amazed at how easy it was to deploy any language model with Ollama. I even made a video on how to put tiny…Apr 8A response icon1Apr 8A response icon1
Published in𝐀𝐈 𝐦𝐨𝐧𝐤𝐬.𝐢𝐨Unlocking Causality in Time Series Predictions: how AI can aid novel therapies for strokeArtificial Intelligence (AI) has revolutionized time series analysis, pushing boundaries across finance, healthcare, and climate science…Jan 24A response icon1Jan 24A response icon1
Published inTowards AIHow I Built an LLM App Based on Graph-RAG System with ChromaDB and ChainlitEnd-to-end app with GUI and storing new knowledge on vector database in just 3 scriptsDec 21, 2024A response icon3Dec 21, 2024A response icon3
Published inOf Brains and MenLLMs for allList of resources from fine-tuning, to RAG, to AI agents, etcNov 10, 2024Nov 10, 2024
Published inILLUMINATION“Why Greatness Cannot be Planned”the hard truth of how to succeed in academia and startup without killing yourselfOct 31, 2024A response icon3Oct 31, 2024A response icon3