Hugging Face's logo
Diwank Tomer's picture
29 357 3937

Diwank Tomer PRO

diwank
xszheng2020's profile picture ShimizuYuki's profile picture alvdansen's profile picture
·
https://diwank.name

AI & ML interests

None yet

Articles

Organizations

Top Secret Org's profile picture Julep AI's profile picture Julep Archive's profile picture Social Post Explorers's profile picture SNBTech's profile picture julep-x-kupid's profile picture

Posts 2

view post
Post
2093
Just published "CryptGPT: A Simple Approach to Privacy-Preserving Language Models Using the Vigenere Cipher".

https://huggingface.co/blog/diwank/cryptgpt-part1

tl;dr - we pretrained a gpt-2 tokenizer and model from scratch on a dataset encrypted with Vigenere cipher and it performs as well as regular gpt-2. Except in order to use it, you need to know the encryption key.

links:
https://github.com/creatorrr/cryptgpt
diwank/cryptgpt
diwank/cryptgpt-large
view post
Post
1590
Really excited to read about Kolmogorov Arnold Networks as a novel alternatives to Multi Layer Perceptrons.

Excerpt:
> Kolmogorov-Arnold Networks (KANs) are promising alternatives of Multi-Layer Perceptrons (MLPs). KANs have strong mathematical foundations just like MLPs: MLPs are based on the universal approximation theorem, while KANs are based on Kolmogorov-Arnold representation theorem. KANs and MLPs are dual: KANs have activation functions on edges, while MLPs have activation functions on nodes. This simple change makes KANs better (sometimes much better!) than MLPs in terms of both model accuracy and interpretability.

https://github.com/KindXiaoming/pykan

Collections 5