fe1ixxu Goto Github PK

alma

State-of-the-art LLM-based translation models.

better_mmt

better_mt_encoder

MT and encoder system for BETTER

bibert

This is the repository of the EMNLP 2021 paper "BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation".

cd_id_mmt

This is repository for our paper

cn-intra-domain

contextual_mapping

dygiepp

Span-based system for named entity, relation, and event extraction.

fairscale

Fairscale for MoA

fairseq-encoder

fairseq-for-en-ar

fe1ixxu

Config files for my GitHub profile.

gradual-finetune

image_expansion

intra-distillation

This is the repository for our EMNLP 2022 paper "The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains".

isss

Invisble Seccurity Signature System

lms_fd

This is the repository for our EMNLP 2023 paper: Condensing Multilingual Knowledge with Lightweight Language-Specific Modules.

mimo_ofdm

k-Modular Quadratic Programming Algorithm for PAPR in MIMO OFDM

mixed-gradient-few-shot

This is the repository of the Findings of NAACL 2022 paper "Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer".

mmt

moadapter

self-distillation

starter-academic

stratified_mixture_of_experts

This is the repository for our EMNLP 2023 paper: Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity.

trl

Train transformer language models with reinforcement learning.

vae-gan

vt-stower

zeroshot-crossling-parsing