yash bhaskar's Projects
Personal Collection of Algorithms used in CP
Contains Code for Simple C task written in Assembly
This project allows you to engage in interactive conversations with your PDF documents using LangChain, ChromaDB, and OpenAI's API. With this powerful combination, you can extract valuable insights and information from your PDFs through dynamic chat-based interactions.
Demoss any code written in .c and .cpp
The project focuses on addressing the challenges of code-mixed machine translation, specifically from Hinglish to English.
This endeavor delves into the world of data analysis, extracting valuable insights and patterns from diverse sources. Explore the findings to uncover the hidden gems within this extensive dataset.
This code performs PDF layout analysis and optical character recognition (OCR) using the layoutparser library and Tesseract OCR Engine. It detects the layout of a PDF document and extracts text from specific regions. The code is divided into several sections, each serving a specific purpose.
DNA course project
Implementation of the paper, "Deep contextualized word representations" - https://arxiv.org/abs/1802.05365v2
Explore this GitHub repository housing 3 versions of Falcon code for text generation. Each version leverages distinct libraries and models, enabling diverse approaches to generating textual responses. Discover the possibilities within!
Collection of Falcon_7B_H20 model, Falcon_7b_4bit_Quantization model, DataBrick_Dolly_v2_3B model, GPT_Medium model, Facebook_OPT_1.3B and Facebook_Open_Llama_3B model.
Implemented BiDirectional Long Short- Term Memory (BiLSTM) to build a Future Word Prediction model. The project involved training these models using large datasets of textual data and tuning hyperparameters to optimize the accuracy of the model.
Specify what you want it to build, the AI asks for clarification, and then builds it.
I implemented the website's functionality using MongoDB, Express, React, and Node.js, and utilized various libraries and frameworks such as Redux, Bootstrap, and Axios. Chat Feature was integrated to chat between users on the platform.
This project explores the impact of memes on contemporary culture, examining their influence on social dynamics and communication. Discover insights into the profound role memes play in shaping our collective consciousness.
Reimplementation and exploration of the Lion optimization method, as described in the original paper "Lion," and its comparative analysis with several widely-used optimization algorithms, including AdamW, Stochastic Gradient Descent (SGD) with momentum, Nesterov Accelerated Gradient (Nesterov AG), AdaGrad, and RMSProp.
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Experience seamless user authentication with our simple yet secure interface. Easily log in and log out to access your personalized account and manage your profile effortlessly.
Experience the power of neural networks in accurately tagging parts of speech. Enhance language analysis and understanding with this advanced POS tagger powered by artificial intelligence.
NFS-System: Scalable Network File System Implementation with Dynamic Server Management and Fault Toleranc
Contains Models for : Question Answering, Future Word Prediction, POS Tagging, Word Embedding, Analyising Twitter Scaped Data, Semantic Similarity
Fine-tunned and Ensembled BERT + BIDAF + BiLSTM + Distil Bert each trained for the task of Question-Answering for the SQUAD v2.0 Dataset