Name: Vivek Chauhan
Type: User
Bio: I am Vivek Chauhan. Currently, I am doing B.Tech from Dronacharya College of Engineering in Computer Science. I like coding. I love to use what I have learned .
Location: 136/4,Gali No 10,Ghandhinagar, Gurugram, Haryana
Vivek Chauhan's Projects
This project focuses on predicting mental fitness using various machine learning algorithms. The dataset contains information about mental health disorders across different countries and years. The goal is to build a predictive model that can accurately estimate mental fitness based on the provided data.
In this project, we fine-tune a FLAN-T5 model to generate less toxic content with Meta AI's hate speech reward model. The reward model is a binary classifier that predicts either "not hate" or "hate" for the given text. You will use Proximal Policy Optimization (PPO) to fine-tune and reduce the model's toxicity.
We are Fine-tuning the CodeLlama-7b parameters model using PEFT Quantization method
This repository contains code for performing dialogue summarization using Hugging Face's Transformers library. The code demonstrates the process of fine-tuning a pre-trained sequence-to-sequence model on a dialogue summarization dataset and evaluating the performance using various metrics.
🚀✨ Help beginners to contribute to open source projects
An AI Career Counselor Application which helps to find the best suited career path for the people
This project focuses on predicting stock market behaviors (Buy, Sell, or Hold) using machine learning algorithms. It incorporates technical indicators and advanced data analysis to provide insights into potential trading decisions. Through a streamlined interface, users can explore market predictions and gain actionable insights for investment.
DialogSum is a project that leverages the FLAN-T5 model for automatic text summarization of dialogues. It utilizes Hugging Face's Transformers library and a custom dataset for training and evaluation.
Tinygrad is a lightweight deep learning framework designed for educational purposes. It offers a minimalistic implementation of automatic differentiation and neural network modules.