Unclaimed profileBuilt from public GitHub and Hugging Face activity. Prithivida has not joined Lounge yet.Claim it
Not on Lounge yet
Prithivida
developerDense, Sparse and Hybrid Embeddings for LLMs, Multimodal Modelling & Data Engineering. Checkout my (YouTube series on V+L, linked below)
Public projects
FlashRank
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.
Pythoncross-encoderfull-text-searchhybrid-search
Styleformer
A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual, active/passive, and many more. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.
Pythonactiveformal-languagesinformal-sentences
ZSIC
Zero Shot Image Classification but more, Supports Multilingual labelling and a variety of CNN based models for a vision backbone by using OpenAI CLIP for $ conscious uses (Super simple, so a 10th-grader could totally write this but since no 10th-grader did, I did) - Prithivi Da
Pythonimage-classificationimage-classifierimage-labeling
Applied-ML-from-1st-principles
Companion Repo for the book The Applied ML Field Manual, Prithiviraj Damodaran
Jupyter Notebookmachinelearningmachinelearningengineeringmlfromscratch
flashembed
Lightweight Python library to add low-footprint (all-MiniLM-* equivalent) multilingual retrievers to your RAG and Search & Retrieval pipelines.
Python
lateness
A ModernColBERT lib that allows you to do 1.) Cheap and lightweight retrieval and 2.) heavy GPU accelerated indexing into vectorDBs that offers native multi-vector support like Qdrant, Vespa and more..
Python
Likely stack
OpenAIVector DB
