avmb Goto Github PK

clweadv

Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders

deep-nmt-architectures

Training scripts for paper Miceli Barone et al. 2017 "Deep Architectures for Neural Machine Translation"

deepnl

Deep Learning for Natural Language Processing

dialogllmscenic

Dialogue-based generation of self-driving simulation scenarios using Large Language Models

dl4mt-lm

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

flowcrosslingualembeddings

NAACL 2019 paper: Density Matching for Bilingual Word Embedding (Zhou et al., 2019)

hackathon_chatarena

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

introdeeplearning

Course material for the Introduction to Deep Learning course

inverse-scaling-eval-pipeline

Basic pipeline for running different sized GPT models and plotting the results

inverse_scaling_mt_paper_version

inverse_scaling_prize_code_identifier_swap

Submission to the inverse scaling prize

lm-robustness

Robust recurrent language model with Random Network Distillation

lowrank-gru

Gated Recurrent Unit with Low-rank matrix factorization

lowrank-highwaynetwork

Low-rank Highway Networks

lowrank-lstm

Low-rank plus diagonal LSTM

lrn

Source code for "A Lightweight Recurrent Network for Sequence Modeling"

marian-dev-wmt2020

Fast Neural Machine Translation in C++ - development repository

marian-mbart

Training harness to pretrain a mBART model using Marian

mosesdecoder

Moses, the machine translation system

mt_scaling_prompt_injection

Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks

nematus

neurallmreorderer

Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation.

theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.