Amit Singh Bhatti·Nov 6, 2024The Achilles’ Heel of LLM Inference Performance - Quantizing ActivationsTaming the Beast of Quantizations of Activations
Amit Singh Bhatti·Mar 7, 2024More than huggingface imports — LLM Internals Part -1A comprehensive guide to understanding the evolution of LLMs and the SOTA architectures with implementation details.
Amit Singh Bhatti·Feb 3, 2024Unveiling the ‘G Factor’ in Language Models : A Leap Towards Understanding LM’S General…In the realm of artificial intelligence (AI), the quest to imbue machines with human-like intelligence has been a guiding star. Much like…
Amit Singh Bhatti·Aug 15, 2023The AI Oppenheimer MetempsychosisRecently, I watched the movie Oppenheimer and the one thing that hit me hard was the current situation of the so-called “Artificial…
Amit Singh Bhatti·Nov 2, 2022AI Explanation Mining — My Thesis AnecdoteRecently, I finished my Master’s thesis which subsides in the domain of AI explanation alignment. There is already work on AI alignment…
Amit Singh Bhatti·Nov 16, 2021Why AI has an “A”? Dark Matter of Intelligence— Missing General Human Intelligence MatterWhile the question that needs to sit on the top of the mountain of the Human parallel intelligence research community is how and when…
Amit Singh Bhatti·Sep 5, 2021Artificial General Attention EconomicsAn explanation to the ECAN, which proposes a dynamic attention architecture defined in the OpenCog system.