Language Modeling Python Packages

besser

A Python-based AI-enhanced low-code open-source platform for smart software development

log-depth-recurrent-modeling

Explorations into the Log Depth Recurrent Modeling proposed by Yiqin Wang of Imperial College London

tape-proteins

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.

bio-embeddings-tape-proteins

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.

gated-state-spaces-pytorch

Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch

surprisal

A unified interface for computing surprisal (log probabilities) from language models! Supports neural, symbolic, and black-box API models.

generate-sequences

A python package made to generate sequences (greedy and beam-search) from Pytorch (not necessarily HF transformers) models.

emoloss

[ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)

codeprep

A toolkit for pre-processing large source code corpora

giganticode-dataprep

A toolkit for pre-processing large source code corpora

pyxlstm

Efficient Python library for Extended LSTM with exponential gating, memory mixing, and matrix memory for superior sequence modeling.

panini-lang

a linguistic analysis/feature extraction framework, LLM-powered

simctg

[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation

lemmes

lema for spanish

harmon

Research chess opponent model trained on human games to reason about likely human mistakes.

rezero

Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"

giganticode-codeprep

A toolkit for pre-processing large source code corpora

simctgbeta

[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation