KranthiGV

products

NYU DevOps Products Service Spring 2023

bias-evaluation

We study the general trend in bias reduction as newer pre-trained models are released. Three recent models ( ELECTRA, DeBERTa and DistilBERT) are chosen and evaluated against two bias benchmarks, StereoSet and CrowS-Pairs. They are compared to the baseline of BERT using the associated metrics

kranthigv.github.io

models

Models built with TensorFlow

Pretrained-Show-and-Tell-model

This repository contains pretrained Show and Tell: A Neural Image Caption Generator implemented in Tensorflow.

transport-efficiency-analysis

hummingbird

Hummingbird compiles trained ML models into tensor computation for faster inference.

KranthiGV/Pretrained-Show-and-Tell-model

This repository contains pretrained Show and Tell: A Neural Image Caption Generator implemented in Tensorflow.

KranthiGV/bias-evaluation

We study the general trend in bias reduction as newer pre-trained models are released. Three recent models ( ELECTRA, DeBERTa and DistilBERT) are chosen and evaluated against two bias benchmarks, StereoSet and CrowS-Pairs. They are compared to the baseline of BERT using the associated metrics

KranthiGV/models

Models built with TensorFlow

KranthiGV/kranthigv.github.io

KranthiGV/transport-efficiency-analysis

KranthiGV/biomedical

Tools for curating biomedical training data for large-scale language modeling

KranthiGV/cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

KranthiGV/cyanure

Cyanure: An Open-Source Toolbox for Empirical Risk Minimization

KranthiGV/espresso

☕️

KranthiGV/g-meghana-reddy.github.io

This is my personal website.

KranthiGV/hummingbird

Hummingbird compiles trained ML models into tensor computation for faster inference.

KranthiGV/inat_comp_2018

CNN training code for iNaturalist 2018 image classification competition

KranthiGV/Jivadah

KranthiGV/lilac

Curate better data for LLMs

KranthiGV/mentorAI

KranthiGV/mteb

MTEB: Massive Text Embedding Benchmark

KranthiGV/multi-needle-in-a-haystack

KranthiGV/nilearn

Machine learning for NeuroImaging in Python

KranthiGV/numpy

Numpy main repository

KranthiGV/onnxmltools

ONNXMLTools enables conversion of models to ONNX

KranthiGV/PocketFlow

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

KranthiGV/pytorch-inference-pipeline

KranthiGV/RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

KranthiGV/Sensor-Data-Visualization

KranthiGV/Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

KranthiGV/tika

Mirror of Apache Tika

KranthiGV/wsdc-task

Task for WSDC Web Applications team.