
Data Science and ML Engineer
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AutoQuantLLM
August 2, 2024 – August 14, 2024
AutoQuantLLM is an efficient and flexible tool designed to help you quantize machine learning models with ease. Supporting multiple quantization methods and types, this tool allows you to optimize your models for deployment or improve their inference speed.
View Projectopen-llm-server
July 17, 2024 – September 4, 2024
This Open LLM Framework serves as a powerful and flexible tool for serving endpoints for embeddings and chat completions using SOTA open source language models. By leveraging models Transformers, this enables various natural language processing (NLP) tasks to be performed via simple HTTP endpoints similar to openai endpoints.
View Projectrag-with-llms
December 19, 2023 – September 6, 2024
This repository implements a Retrieval-Augmented Generation (RAG) approach leveraging advanced Language Models (LLMs). RAG combines the power of pre-trained LLMs with efficient information retrieval, enabling context-aware and coherent content generation.
View ProjectVectorDB
December 19, 2023 – January 3, 2024
This repository contains an implementation of a Vector Database, a specialized database designed for efficient storage and retrieval of high-dimensional vectors. Ideal for applications such as machine learning, similarity search, and data analysis.
View Projecttext-generator-LSTM
May 18, 2023 – May 18, 2023
Automatic text generation using LSTM networks for generating text similar to a given input
View Projectclassification-with-nlp-xgboost-and-pipelines
May 14, 2023 – May 14, 2023
This is a simple Flask API that provides wine variety classification based on their descriptions. The API uses an XGBoost model and an NLTK tokenizer to perform the classification.
View Projectbuild_etl_pipeline
May 4, 2023 – May 13, 2023
This project provides a simple example of building an ETL (Extract, Transform, Load) pipeline using Python and SQL. The pipeline extracts data from a CSV file, applies some transformations to the data, and loads the transformed data into a SQLite database.
View ProjectEDA
May 2, 2023 – May 8, 2023
This EDA repository covers essential topics such as data cleaning, handling missing values, feature engineering, and visualizations.
View Projectestimators-from-scratch
April 23, 2023 – February 18, 2024
This project provides Python implementations of various estimators from scratch, without relying on external libraries such as scikit-learn. The purpose of this project is to understand how these models work under the hood.
View Project