An LSP proxy to run LSP inside Docker containers.

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Sparsify transformers with SAEs and transcoders

Hydra is a framework for elegantly configuring complex applications

An Easy-to-use Knowledge Editing Framework for LLMs.

A framework for few-shot evaluation of autoregressive language models.

Self-hardening firewall for large language models

[NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.