PinnedBhavin Jawade, Ph.D·Jul 14, 2025Understanding MatFormerMatryoshka Styled Nested Transformers For Compute Efficient Inference — MatFormer used in Gemma 3n
PinnedBhavin Jawade, Ph.D·Aug 29, 2024ORPO — Preference Optimization without Reference ModelCombing Instruction Fine-tuning and Preference Alignment in a single stage.
PinnedInTDS ArchivebyBhavin Jawade, Ph.D·Jan 4, 2024Tuning-Free Longer Context Lengths For LLMs — A Review of Self-Extend (LLM Maybe LongLM)A simple strategy to enable LLMs to consume longer context length inputs during inference without the need for finetuning.A response icon1A response icon1
PinnedInTDS ArchivebyBhavin Jawade, Ph.D·Dec 27, 2023Demystifying GQA — Grouped Query Attention for Efficient LLM Pre-trainingThe variant of multi-head attention powering LLMs like LLaMA-2, Mistral7B, etc.A response icon3A response icon3
PinnedInTDS ArchivebyBhavin Jawade, Ph.D·Dec 22, 2023Understanding LoRA — Low Rank Adaptation For Finetuning Large ModelsFine-tuning large pre-trained models is computationally challenging, often involving adjustment of millions of parameters. This…A response icon4A response icon4
Bhavin Jawade, Ph.D·Oct 30, 2019Nothing has everythingA mathematical viewpoint.A response icon1A response icon1
Bhavin Jawade, Ph.D·Dec 24, 2018Training HaarCascade Model on Microsoft Azure.In this hands-on tutorial, we will learn how to train your own haar cascade model on Microsoft Azure. To understand Haarcascade I…A response icon2A response icon2
InTDS ArchivebyBhavin Jawade, Ph.D·Jul 8, 2018Quantum Computing ?/!Zeros and ones. This is how we imagined computing till now. This is what classical computing is. But a whole new concept is now changing…A response icon1A response icon1
Bhavin Jawade, Ph.D·Oct 18, 2017Blockchain ?/ ! The Start of a new revolutionToday every big company you can think of is investing in Blockchain. From Tech giants like Microsoft and IBM to Financial giants like…A response icon1A response icon1
