ruizheliUOA

DLP-LoRA

DLP-LoRA An efficiency dynamic LoRA plugin

nnsight

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Anchored_Bias_GPT2

This is the official code for anchored bias of GPT2

Awesome-Interpretability-in-Large-Language-Models

This repository collects all relevant resources about interpretability in LLMs

HR-VAE

Code for the paper "A Stable Variational Autoencoder for Text Modelling"

TWR-VAE

Improving Variational Autoencoder for Text Modelling withTimestep-Wise Regularisation

reading_group

ruizheliUOA/Awesome-Interpretability-in-Large-Language-Models

This repository collects all relevant resources about interpretability in LLMs

ruizheliUOA/HR-VAE

Code for the paper "A Stable Variational Autoencoder for Text Modelling"

ruizheliUOA/TWR-VAE

Improving Variational Autoencoder for Text Modelling withTimestep-Wise Regularisation

ruizheliUOA/Anchored_Bias_GPT2

This is the official code for anchored bias of GPT2