Skip to content
View aashu-0's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report aashu-0

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
aashu-0/README.md

👋 Hi, I'm Aashutosh

Currently building with LLMs, agents, deep learning — and the systems that put them into production.


🛠️ What I've worked on

Area What I did
Deep learning & model implementation Built architectures from first principles
LLMs Fine-tuned and instruction-tuned open models, ran them locally
RAG Built retrieval pipelines over text, documents, and multimodal data
Multi-agent systems Orchestrated agents and DAG workflows with LangGraph
Computer vision Trained classifiers and generative models, applied transfer learning
Applied ML Shipped end-to-end classical machine learning on real-world data
Backend development Built APIs with databases and authentication
MLOps Set up CI/CD, experiment tracking, containerization, and orchestration
Model deployment Served models to the cloud and built interactive demos

🧰 Tools & Technologies

Languages Python JavaScript SQL HTML5 CSS3
Deep Learning & ML PyTorch scikit-learn NumPy pandas OpenCV
LLMs, RAG & Agents Hugging Face LangChain LangGraph Ollama
Backend FastAPI SQLAlchemy Pydantic Jinja
MLOps & Deployment Docker Kubernetes MLflow DVC GitHub Actions Streamlit Gradio AWS

🔗 Links

LinkedIn X Email

Pinned Loading

  1. MLOps_Learning_Project MLOps_Learning_Project Public

    An end-to-end MLOps project demonstrating sentiment analysis on IMDb movie reviews with complete CI/CD pipeline, experiment tracking, model registry, and production deployment on AWS EKS.

    Python 1

  2. FineTuning_GPT2 FineTuning_GPT2 Public

    PyTorch implementation of GPT-2 that loads pretrained weights and enables instruction fine-tuning on the Stanford Alpaca dataset.

    Jupyter Notebook

  3. UNet-Polygon-Colorization UNet-Polygon-Colorization Public

    A Conditional UNet architecture with color embedding to generate accurate colored outputs from grayscale polygon outlines.

    Jupyter Notebook

  4. multiagent_debate_dag multiagent_debate_dag Public

    Multi-Agent Debate DAG using LangGraph

    Python

  5. Career-Domain-Prediction Career-Domain-Prediction Public

    course project. machine learning tool that predicts suitable career domains for students based on their academic background, interests, and skills using survey data and classification models.

    Jupyter Notebook 1

  6. fine-tuned-llama3-7B fine-tuned-llama3-7B Public

    Fine tuning Llama 3 7B and 8B

    Jupyter Notebook