Language Modeling Python Packages | PyPI Stats

besser

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

10K 168 33

tape-proteins

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

2K 739 135

panini-lang

a linguistic analysis/feature extraction framework, LLM-powered

1K 0 0

gated-state-spaces-pytorch

Gated State Spaces - GSS - Pytorch

1K 102 4

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.

806 739 135

surprisal

A package to conveniently compute surprisals for text sequences and subsequences

523 52 11

generate-sequences

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

477 18 2

giganticode-dataprep

A toolkit for pre-processing large source code corpora

352 45 10

emoloss

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

335 128 13

lemmes

lema for spanish

298 0 0

pyxlstm

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

234 306 28

codeprep

A toolkit for pre-processing large source code corpora

208 45 10

simctg

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

171 476 40

giganticode-codeprep

A toolkit for pre-processing large source code corpora

108 45 10

rezero

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

77 415 53

simctgbeta

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

41 476 40