Skip to content
View deeepsig's full-sized avatar
πŸ’
monk focus
πŸ’
monk focus

Highlights

  • Pro
Block or Report

Block or report deeepsig

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
deeepsig/README.md

Hey, I'm Deepak


About Me

Hey there, I'm Deepak!

I'm a student based in India πŸ±β€πŸ where I study software engineering. When I'm not obsessing over my notion site, I'm learning new technologies, building interesting apps that solve my problems (and hopefully of others), and discussing architecture and startups with my friend.

Looking for new grad opportunities in 2024.

Tech Stack: Python, NodeJS, React, C/C++, LLMs, fastai, Pytorch.

Latest work: I built a python library called tokviz which is available on PyPI. tokviz is a Python library for visualizing tokenization patterns across different language models. This library offers a comprehensive platform for researchers, data scientists, and NLP enthusiasts to gain insights into how different language models process and tokenize text.

Try it on your projects: https://pypi.org/project/tokviz/ Documentation: https://github.com/deeepsig/tokviz

Please email me! I like people. email: [email protected] πŸ“© Or just send in a LinkedIn message πŸ˜„

Pinned

  1. tokviz tokviz Public

    tokviz is a Python library for visualizing tokenization patterns across different language models.

    Python 6

  2. rag-ollama rag-ollama Public

    A Retrieval Augmented Generation (RAG) system using LangChain, Ollama, Chroma DB and Gemma 7B model.

    Jupyter Notebook 9

  3. llm-tokenization-visualizer llm-tokenization-visualizer Public

    A notebook that let's you analyze the tokenization pattern in multiple LLMs.

    Jupyter Notebook

  4. ReadingRhythms ReadingRhythms Public

    ReadingRhythms helps readers find the best music playlist that they can listen to while reading their favorite novel, manga or manhwa in order to maximize their reading experience.

  5. query-translation query-translation Public

    Implementation of papers on query translation

    Jupyter Notebook