Ashish Kumar Sinha
Machine Learning Engineer and Researcher.
Home
Notebooks
About
Résumé
Low-Rank Adaptation (LoRA) for BERT Classification
Supervised Fine-Tuning (SFT) on a Tiny Language Model
Supervised Fine-Tuning (SFT) for LLMs
Democratizing LLM Inference with Quantization Techniques
How Low-Rank Adaptation (LoRA) Changes the Geometry of Self-Attention
Parameter Efficient Fine Tuning (PEFT) – Adapting Large Models at Scale
Imitation Learning - How to make it work?
Frequent Itemset Mining
Self Attention Mechanism - Learning Contextualized Embeddings
huberLLM - Retrieval Augmented LLM for Huberman Podcast
Graph Convolutional Nets - Basics
Node2Vec - Word2Vec in disguise (?)
huberLLM - Retrieval Augmented LLM for Huberman Podcast