PinnedPart 1: Step-by-Step Dataset Creation- Unstructured to Structuredin collaboration with Nitin Tiwari (ML GDE)Apr 9, 2024Apr 9, 2024
PinnedPart 2: Fine Tune — Gemma 2b-it modelin collaboration with Nitin Tiwari (ML GDE)Apr 9, 20241Apr 9, 20241
PinnedGemma is Here ✨Gemma is a Latin word for precious stone but at Google, it’s a state-of-the-art model inspired and driven by the same research as Gemini…Feb 23, 2024Feb 23, 2024
🚀Summary Blog: Self-Taught EvaluatorsIn the evolving field of AI and machine learning, large language models (LLMs) require robust evaluators to ensure their responses align…Aug 18, 2024Aug 18, 2024
🚀Summary Blog: 500xCompressor: Generalized Prompt Compression for Large Language ModelsLarge Language Models (LLMs) have revolutionized natural language processing (NLP), but they face challenges when dealing with long…Aug 15, 2024Aug 15, 2024
🛰️Summary Blog — RaVÆn: unsupervised change detection of extreme events using ML on‐board…Ever wondered about the colossal machinery orbiting above us, thousands of miles away? How does it function? Can it match the capabilities…Aug 14, 20241Aug 14, 20241
Published inGoPenAI🚀Summary Blog: ReLU Strikes Back: Harnessing Activation Sparsity in Large Language ModelsIntroduction to Large Language Models (LLMs) and ReLUAug 12, 2024Aug 12, 2024
Published inGenerative AI🚀Summarizing HALVA: Hallucination Attenuated Language and Vision AssistantA recent research by Google Research team that uses a contrastive tuning strategy to mitigate hallucinations in multimodal LLMs responses.Aug 10, 2024Aug 10, 2024
Published inGenerative AI🚀Summary Blog: Is Cosine Similarity of Embeddings Really About Similarity?Large Language models have seen a huge boom in production recently, with companies pouring such models in various sizes, their applications…May 22, 2024May 22, 2024
