This repository collects all relevant resources about interpretability in LLMs

A library for mechanistic interpretability of GPT-style language models

BEAR dataset

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

implementation of ICML 2018 paper, Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

A library to create and manage configuration files, especially for machine learning projects.

OpenZeppelin Contracts is a library for secure smart contract development.

emoji2vec: Learning Emoji Representations from their Description

Predictive Power Score (PPS) in Python

Unsupervised Extractive Summarization based on Position-Augmented Centrality

State-of-the-Art Text Embeddings

Hopfield Network implemented with Python

Fine-tuning BART on COVID Dialogue Dataset

Dataset for the Emerging & Novel Entity NER task (WNUT '17)

A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.

Library for Knowledge Intensive Language Tasks

Twitter named entity extraction for WNUT 2016 http://noisy-text.github.io/2016/ner-shared-task.html

KaLM at SemEval-2020 Task 4: Knowledge-aware Language Models for Comprehension And Generation

A tool for extracting plain text from Wikipedia dumps

Initial commit

simple implementation of LSTM-CRF for NER using pytorch