Skip to content
View veezbo's full-sized avatar
18 followers · 14 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2

Block or report veezbo

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
veezbo/README.md

👋

AI, Research, Engineering, Philosophy

Hi! My name is Vibhor Kumar. I'm a computer scientist, amateur neuroscientist, and armchair philosopher of science. I like working at the intersection of the theoretical and applied. My work has been involved in mapping fly brains, catching financial fraud, and generating assets of various types using AI.

I currently work on the Trust & Safety team @Tinder where I combine skills in ML, Data Science, and Backend to catch bad actors and keep Tinder safe. I also advise AI startups on the side.

Feel free to check out my personal website at veezbo.com to learn more!

📚🧠 I’m currently working on

AkkadianOracle: Understanding Ancient Peoples through Conversation

Repo: https://github.com/veezbo/akkadian_oracle
Live Demo: https://poe.com/AkkadianOracle

A chatbot built using the Poe platform on top of ChatGPT and GPT-4 with Retrieval-Augmented Generation (RAG) with my released Akkadian English corpus

Additional experiments involve pre-trained LLM fine-tuning as well as PEFT (with QLoRA). Notebooks included in the repo.

Research paper to be posted soon

Llourney: Stable Diffusion with a fine-tuned LLM instead of CLIP

Repo: https://github.com/veezbo/llourney-dev
Collaborators: @dg845 @andrewryanchama

Exploring the feasibility of replacing CLIP with an LLM fine-tuned using a frozen Stable Diffusion model and diffusion training loop.

🌐🤝 Recent contributions to open-source AI

veezbo/akkadian_oracle
veezbo/akkadian_english_corpus - corresponding HuggingFace dataset
dottxt-ai/outlines#287
huggingface/transformers#25807

🔗 Connect with me

Personal Website LinkedIn HuggingFace Substack Discord Email

Pinned Loading

  1. akkadian_oracle akkadian_oracle Public

    Implementation of a chatbot that lets you communicate with someone from 3000 years ago in Ancient Mesopotamia. How does their common sense understanding and worldview differ from yours?

    Jupyter Notebook 2

  2. llourney-dev llourney-dev Public

    Stable Diffusion with an LLM instead of CLIP

    Jupyter Notebook 4 1

  3. single_file_seq2seq single_file_seq2seq Public

    A seq2seq transformer from scratch in a single file. Optimized for readability and learnability.

    Python 2

  4. single_file_gpt single_file_gpt Public

    A GPT from scratch in a single file. Optimized for readability and learnability.

    Python 4