Skip to content
View AashiDutt's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report AashiDutt

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AashiDutt/README.md

💫 About Me:

🙋‍♀️I'm an ML enthusiast who likes to explore new technologies, write code, and ask a lot of questions.

⭐️ Google Developer Expert in Machine Learning (Gen AI)

👩🏻‍🎓MS Candidate at Georgia Institute of Technology

🔭 I’m currently working on understanding the basics of LLM and applying learnings to projects

👯 I’m looking to collaborate on Gen AI projects

📝 I regularly write technical blogs on research paper summaries for LLMs, RLHF, and related projects.

🌐 Socials:

LinkedIn Medium X YouTube

💻 Tech Stack:

C Python Solidity Google Cloud Keras Matplotlib NumPy Pandas TensorFlow Scipy Plotly PyTorch scikit-learn Adobe Figma Dribbble Canva Adobe Photoshop Jira Power Bi Trello Raspberry Pi Arduino Notion

Projects

1. Pdf Chatbot

Gradio application that allows users to upload any pdf and ask questions related to the document using llama3 running locally using Ollama.

Demo

pdf_chatbot

Project Link

(https://github.com/AashiDutt/RAG/tree/main/%5BPROJECT%5Dpdf_chatbot)

2. Chat with Webpage

A web-based chat application that helps to chat with any webpage using local llama3 and RAG. Developed using Streamlit, ollama and langchain_community.

Demo

webpage_chatbot (1)

Project Link

https://github.com/AashiDutt/RAG/blob/main/%5BPROJECT%5DRAG_with_llama3_webpage_chatbot.py

3. AI Architect

SDXL fine-tuning with DreamBooth and LoRA for image generation of living rooms and video generation using Stable Video Diffusion by Stability AI hosted on HuggingFace.

Demo

svd

Project Link

https://github.com/AashiDutt/LLM-Projects/blob/main/AI_Architect_fine_tuning_stable_diffusion_with_Dreambooth_and_LoRA.ipynb

4. PharmaScan

The PharmaScan app, is powered by revolutionary Gemini Pro Vision API that empowers you to scan your medicines and analyze them for instant prescription information. This app takes an image of any medicine and generates a prescription instantly covering the medicine name, symptoms it cures, primary diagnosis, dosage, and method of use.

Demo

compressed (2) (1) Gemini_Pro_Vision_App (2)

Project Link

https://github.com/NSTiwari/Medicine-Scan-with-Gemini/blob/main/README.md

Interesting Reads

  1. LoRA: Squeezing Giants into Ants with Style
  2. PharmaScan
  3. Generative Image Dynamics

📊 GitHub Stats:




Pinned Loading

  1. FarmScan-using-Gemini FarmScan-using-Gemini Public

    Forked from NSTiwari/FarmScan-using-Gemini

    This project is an implementation of using the Google Pro Vision model API on Android to recognize the freshness and nutrition value of fruits and vegetables.

    Kotlin 1

  2. Medicine-Scan-with-Gemini Medicine-Scan-with-Gemini Public

    Forked from NSTiwari/Medicine-Scan-with-Gemini

    PharmaScan is an Android application that leverages Gemini Pro Vision model to identify medicines and provide their details such as usage, dosage, diagnosis, etc. on-the-go.

    Jupyter Notebook 3

  3. Stable-DiffusionXL-using-DreamBooth-and-LoRA-on-Android Stable-DiffusionXL-using-DreamBooth-and-LoRA-on-Android Public

    Forked from NSTiwari/Stable-DiffusionXL-using-DreamBooth-and-LoRA

    This project is an implementation of fine-tuning an SDXL model using DreamBooth and LoRA on custom data of interior room designs and deploy the model on Android using MediaPipe.

    Jupyter Notebook

  4. LLM-Projects LLM-Projects Public

    Jupyter Notebook 1

  5. Deep-Learning Deep-Learning Public

    Deep Learning Projects using Tensorflow.

    Jupyter Notebook 1

  6. Annotated-Research-Papers Annotated-Research-Papers Public

    This repository contains annotated papers for NLP, Computer vision, Reinforcement learning and more, along with my notes.

    1