Pinned Loading
-
Alignment-Faking-Demo-Llama3B-and-GPT40mini
Alignment-Faking-Demo-Llama3B-and-GPT40mini PublicReplication and extension of Anthropic's Alignment Faking Demo using instead Llama3B and GPT40mini as well as correcting alignment faking using deontological ethics.
Jupyter Notebook 1
-
Automated_Red_Teaming_Tool
Automated_Red_Teaming_Tool PublicA Streamlit-based tool that enables anyone to red team any LLM using API or local access, visualize model behavior, and assess alignment using LLM-as-a-judge reasoning.
-
PyTorch
PyTorch PublicThis repository showcases practical machine learning projects using PyTorch, covering both classical regression and deep learning with CNNs. Designed for clarity and reproducibility, these projects…
Jupyter Notebook
-
Automated_LLM_Evaluations_Tool
Automated_LLM_Evaluations_Tool PublicInteractive LLM evaluation tool incorporating LLM-as-a-judge scoring, with visual outputs to support scalable, safety-focused analysis.
-
Machine-Learning-Projects
Machine-Learning-Projects PublicA collection of university assignments exploring core machine learning and deep learning concepts — from k-NN and decision trees to CNNs and neural network internals — implemented in Python and Colab.
Jupyter Notebook
-
Python-data-processing-projects
Python-data-processing-projects PublicA collection of university assignments showcasing foundational Python skills in data processing, visualization, and scripting — built to support advanced work in AI and machine learning.
Jupyter Notebook
If the problem persists, check the GitHub status page or contact support.