Kranthi Kiran GV's repositories
Pretrained-Show-and-Tell-model
This repository contains pretrained Show and Tell: A Neural Image Caption Generator implemented in Tensorflow.
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
biomedical
Tools for curating biomedical training data for large-scale language modeling
cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
cyanure
Cyanure: An Open-Source Toolbox for Empirical Risk Minimization
g-meghana-reddy.github.io
This is my personal website.
hummingbird
Hummingbird compiles trained ML models into tensor computation for faster inference.
inat_comp_2018
CNN training code for iNaturalist 2018 image classification competition
lilac
Curate better data for LLMs
mteb
MTEB: Massive Text Embedding Benchmark
nilearn
Machine learning for NeuroImaging in Python
numpy
Numpy main repository
onnxmltools
ONNXMLTools enables conversion of models to ONNX
PocketFlow
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
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.
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.
tika
Mirror of Apache Tika
wsdc-task
Task for WSDC Web Applications team.