ok3ks Goto Github PK

activity_prediction

Predicts Activities based on Sensor Measurement. Dataset used for Modelling is the PAMAP3 Dataset

algorithms

"""Handy Algorithms and Data Structures"""

bias_and_ml

This repository creates a machine learning model and further assesses the bias of this model with regards to the features

data-centric-deep-learning

Public repository for the "Data-Centric Deep Learning" course taught by Mike Wu and Andrew Maas. Available at https://corise.com/course/data-centric-deep-learning.

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course

disso-cold

Classification of Long documents. Implementation of state-of-the-art models as well as iteration.

forage-lyft-starter-repo

Lyft starter repo

haystack

:mag: Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-3 and alike). Haystack offers production-ready tools to quickly build ChatGPT-like question answering, semantic search, text generation, and more.

image-segmentation

This project required the matching of submitted colour patterns as an image to the standard colour pattern to be used in a game

imdb_movie_metadata-analysis

The goal of this analysis is to derive insights which informs the production of the next movie. This repository consists of IMDB_movie_metadata csv, a .ipynb file and a presentation reporting findings.

insurance_modelling

llama-2-onnx

llama-cpp-python

Python bindings for llama.cpp

longformer

Longformer: The Long-Document Transformer

microsoft_sentence_completion

A challenge to create models that select the right option to complete a sentence from a series of option. Models are then compared with the human similarity measure.

mlops-zoomcamp

Free MLOps course from DataTalks.Club

ok3ks

Config files for my GitHub profile.

political_spending_uk

Hackathon - Money in politics: how do political parties spend their campaign war chests?

rag

robert_recurrence_over_bert

pyTorch implementation of Recurrence over BERT (RoBERT) based on this paper https://arxiv.org/abs/1910.10781 and comparison with pyTorch implementation of other Hierarchical Methods (Mean Pooling and Max Pooling) and Truncation Methods (Head Only and Tail Only) presented in this paper https://arxiv.org/abs/1905.05583

scrapy

Scrapy, a fast high-level web crawling & scraping framework for Python.

seai

CMU Lecture: Machine Learning In Production / AI Engineering / Software Engineering for AI-Enabled Systems (SE4AI)

sent_analysis

spark_sample_project

Repository detailing my spark learning

sports

Exploring Sports Data using Data Analysis, Data Science and ML

stable-diffusion

A latent text-to-image diffusion model

tabular_data

Tabular Datasets

torchdistill

A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆20 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

tutorials

Notebooks/scripts for youtube tutorials