ayukh
Follow
Stars
Everything you need to build state-of-the-art foundation models, end-to-end.
Structured test tasks and model tuning scripts for multiple subjects from ZNO - the Ukrainian External Independent Evaluation (ЗНО)
Robust recipes to align language models with human and AI preferences
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)
Curated list of Ukrainian natural language processing (NLP) resources (corpora, pretrained models, libriaries, etc.)
Papers and resources related to the security and privacy of LLMs 🤖
A toolkit to assess data privacy in LLMs (under development)
A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)
Guardrails for secure and robust agent development
Feature Clock: High-Dimensional Effects in Two-Dimensional Plots
A curated list of Large Language Model (LLM) Interpretability resources.
A repository of Language Model Vulnerabilities and Exposures (LVEs).
UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language
PiML (Python Interpretable Machine Learning) toolbox for model development & diagnostics
Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
The Urban Planning dashboard that was developed in terms of Interactive Machine Learning: Visualization & Explainability course at ETH Zurich.
High-speed download of LLaMA, Facebook's 65B parameter GPT model
Application for parsing and analyzing CS:GO Demo files. Written in Windors Forms.
Sequence Models by Andrew Ng on Coursera. Programming Assignments and Quiz Solutions.
Scrape the Twitter Frontend API without authentication.
A project written in Python to get old tweets, it bypass some limitations of Twitter Official API.