baselmousi

automated-interpretability

long_stable_diffusion

Model-Parallelism-Workshop

Code and notes associated with the model parallelism workshop. The workshop was delivered by Nvidia.

toxic_spans

Detect toxic spans in toxic texts

NeuroX

A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.

LLMeBench

Benchmarking Large Language Models

multilingual-latent-concepts

Code associated with the ACL24 paper titled, "Exploring Alignment in Shared Cross-Lingual Spaces"

TransformersConceptNet

Code and Data Associated with "Can LLMs facilitate interpretation of pre-trained language models?"

baselmousi/automated-interpretability

baselmousi/long_stable_diffusion

baselmousi/Model-Parallelism-Workshop

Code and notes associated with the model parallelism workshop. The workshop was delivered by Nvidia.

baselmousi/toxic_spans

Detect toxic spans in toxic texts