raoofnaushad/mechanistic_intepreteability

Stars
1
Language
Jupyter Notebook
Created 12 months ago
Updated 12 months ago

raoofnaushad/mechanistic_intepreteability

raoofnaushad

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Explore the interpretability of language models with TransformerLens in this repository. We leverage Hugging Face Transformers and the mechanistic interpretability package to reverse engineer the algorithms learned by these models during training, shedding light on their inner workings.

Land-Cover-Classification-using-Sentinel-2-Dataset

Application of deep learning on Satellite Imagery of Sentinel-2 satellite that move around the earth from June, 2015. This image patches can be trained and classified using transfer learning techniques.

Jupyter Notebook

AWSathena_s3_python

Simple way to query data from S3 using AWS athena and Boto3

sample-tkinter-application-structure

Creating and Structuring Complex Tkinter Applicaton Python - OOP || how to structure and create a Tkinter application with Python. This follows an object oriented approach. The below link will direct you to the blog link with more description on how to do it.

Opencv_Cheatsheet

OpenCV Cheatsheet for essential and advanced Image Processing.

Fourier-Transformation-for-Image-Processing

Jupyter Notebook

EuroSAT_LULC

Jupyter Notebook

rasa_docker_flask_mongodb

A simple intent and entity recognition web app with flask powered by RASA along with mongodb as database containerized using Docker and Docker-Compose

Image-Semantic-Segmentation-of-Satellite-Imagery-using-U-Net.

Image Semantic Segmentation of Satellite Imagery using U-Net. Image segmentation using U-Net architecture on Satellite Imagery with the help of fast.ai framework

Jupyter Notebook

authentication_flask_api_jwt

Simple flask app with authentication using JWT - Python

name_matching_nlp

This repo contains small python scripts for name matching using different techniques.

UNET_SALT_DETECTION

Competition Overview - Source: Kaggle Several areas of Earth with large accumulations of oil and gas also have huge deposits of salt below the surface. But unfortunately, knowing where large salt deposits are precisely is very difficult. Professional seismic imaging still requires expert human interpretation of salt bodies. This leads to very subjective, highly variable renderings. More alarmingly, it leads to potentially dangerous situations for oil and gas company drillers. To create the most accurate seismic images and 3D renderings, TGS (the world's leading geoscience data company) is hoping Kaggle's machine learning community will be able to build an algorithm that automatically and accurately identifies if a subsurface target is salt or not.

Jupyter Notebook

load_testing_locust

A boiler plate for load testing with locust - Python opensource load testing tool

Seq2Seq_QuestionGeneration_NLP

End to end data driven question generation using Seq2Seq (Encoder Decoder Architecture). This repo contains notebooks of approaches step by step.

Jupyter Notebook

GPT-3-Beginner-Workout

This repo contains an introduction to how to use GPT-3 for various simple task.

BreastCancerDetectionProject

IndianDanceForms

Jupyter Notebook

rag_with_chroma

A dynamic exploration of LLaMAindex with Chroma vector store, leveraging OpenAI APIs. This repository contains four distinct example notebooks, each showcasing a unique application of Chroma Vector Stores ranging from in-memory implementations to Docker-based and server-based setups.

Jupyter Notebook

LLAMA-RAG-Workspace

This repository is dedicated to exploring and implementing the LLAMA index and RAG techniques with OpenAI's tools and resources.

Jupyter Notebook

vector_similarity_with_spark

introduction_to_julia

Getting started with Julia language.

astrophysics-_-Awesome-List

This Repo is for Physics Enthusiast who would like to know, read and contribute about Black Holes.

ARIMA_SAMPLE

Jupyter Notebook

elastic_search_text_embeeddings

resume_parser_nlp

End to end resume parser for extracting relevant information from Resumes.

huggingFace-NLP-pieplines

Jupyter Notebook

Simple_Django_Poll_App

matcher

github-actions-demo

Soxy

Soxy is my personal NN library created from scratch using Numpy

Jupyter Notebook

statistics_python_assignment

Computation_thinking_julia

Using the Julia programming language to approach real-world problems in varied areas applying data analysis and computational and mathematical modeling.

Transformer-Reversed-Integer-Seq2Seq

Explore the essence of Transformer architecture with our Python repository. Featuring a minimalist Seq2Seq Transformer, this educational project focuses on reversing integer sequences. Uncover the fundamentals without external libraries, making it an ideal entry point for understanding Transformers. Start your educational journey today.

Jupyter Notebook