Antonio Valerio Miceli Barone's repositories
lowrank-gru
Gated Recurrent Unit with Low-rank matrix factorization
inverse_scaling_prize_code_identifier_swap
Submission to the inverse scaling prize
lowrank-highwaynetwork
Low-rank Highway Networks
deep-nmt-architectures
Training scripts for paper Miceli Barone et al. 2017 "Deep Architectures for Neural Machine Translation"
DialogLLMScenic
Dialogue-based generation of self-driving simulation scenarios using Large Language Models
marian-mBART
Training harness to pretrain a mBART model using Marian
lowrank-lstm
Low-rank plus diagonal LSTM
FlowCrosslingualEmbeddings
NAACL 2019 paper: Density Matching for Bilingual Word Embedding (Zhou et al., 2019)
inverse-scaling-eval-pipeline
Basic pipeline for running different sized GPT models and plotting the results
MT_Scaling_Prompt_Injection
Scaling Behavior of Machine Translation with Large Language Models under Prompt Injection Attacks
neuralLMReorderer
Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
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
lm-robustness
Robust recurrent language model with Random Network Distillation
marian-dev-wmt2020
Fast Neural Machine Translation in C++ - development repository
mosesdecoder
Moses, the machine translation system
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.