diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.

PyTorch native post-training library

Simple, unified interface to multiple Generative AI providers

🦜🔗 Build context-aware reasoning applications

Python code for LLMs surprisals and linear machine learning models

Novoic's linguistic feature extraction library

Entropy Based Sampling and Parallel CoT Decoding

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Multilingual Large Language Models Evaluation Benchmark

https://clap-purdue.github.io/gricean-pragmatics/

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

Repo for webbook and materials of the course "Understanding LLMs" @ Uni Tübingen

SAP Benchmark

Repository for CoNLL 2023 Paper

Tools for language sample analysis.

Learning of degree expressions: a computational approach

The Return of Lexical Dependencies: Neural Lexicalized PCFGs (TACL)

source code of NAACL2021 "PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols“ and ACL2021 main conference "Neural Bilexicalized PCFG Induction"

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Dr.VOT is an a software package for automatic measurement of voice onset time (VOT).

code to compute syntactic surprisal at words in a given sentence

Automatically exported from code.google.com/p/incremental-top-down-parser

Utility for analyzing Transformer based representations of language.

Extract full next-token probabilities via language model APIs

References to the Medium articles

Pecab: Pure python Korean morpheme analyzer based on Mecab