Skip to content
View takeitezybaby's full-sized avatar
1 follower · 0 following

Block or report takeitezybaby

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
takeitezybaby/README.md

Hi, I'm Yash 👋

B.Tech CSE/Data Science student at MIT Manipal (MAHE) · Class of 2028
Building toward AI/ML engineering roles

🔭 What I'm working on

  • Fact-verification RAG system — atomic/scenic chunking, entity-aware retrieval, and a deterministic verdict layer on top of LLM reasoning
  • Fully local video RAG pipeline — semantic Q&A over video using FFmpeg, Whisper, nomic-embed-text, Mistral, and Ollama
  • Neural nets from scratch — working through backprop, MLPs, batchnorm, and transformer internals, hand-deriving gradients and running my own training ablations along the way

🧠 Currently learning

  • Deep learning fundamentals (autograd, optimization, transformers) from the ground up
  • Data structures & algorithms for technical interviews
  • Agentic AI systems (LangChain / LangGraph)

🛠️ Tech I work with

📌 Pinned-worthy projects

Project Description
backstory-rag Fact-verification RAG with entity-aware retrieval and a deterministic verdict layer
local-llm-video-rag Fully local semantic Q&A pipeline over video content
makemore Character-level language model built from scratch, with my own batch-size/regularization ablation on top of the base architecture

LinkedIn · Email

Popular repositories Loading

  1. local-backstory-llm-RAG local-backstory-llm-RAG Public

    Locally hosted RAG pipeline that verifies fictional backstories against a source novel using atomic claim validation, entity-grounded retrieval, and deterministic aggregation.

    Python 2

  2. local-llm-video-rag local-llm-video-rag Public

    Local Retrieval-Augmented Generation system for semantic video Q&A using Whisper, cosine similarity, and Mistral via Ollama.

    Python

  3. neetcode-submissions neetcode-submissions Public

    My NeetCode.io problem submissions

    Python

  4. micrograd micrograd Public

    Jupyter Notebook

  5. makemore makemore Public

    Jupyter Notebook

  6. takeitezybaby takeitezybaby Public