BaohaoLiao

mefts

[NeurIPS2023] Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning

3ml

Official code for 3ML (EMNLP 2022)

ApiQ

Quantize LLM to extremely low-bit, and finetune the quantized LLMs

multiback

Code for the WMT21 paper "Back-translation for Large-Scale Multilingual Machine Translation"

NLP-reproduction

Offer straightforward guidance to reproduce the results of NLP papers.

ApiQ-bw

improved_transformer_v3

pafi_hiwi

Official code for the ACL2023 paper

RevLLaMA

reversible LLaMA finetuned on alpaca dataset

aslfrv4

Code for kaggle competition, Google American Sign Language Fingerspelling Recognition

baohaoliao

github stat

cluster

fairseq-1

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

galore_offline

LLaVA

LLaVA_rosa

lmeval

evaluation of langauge models

LoftQ_partial_lora

LoftQ_v1

lq_lora_v0

multillama

peft

personal_website

pyreft

road

SimMIM

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

tdms

TransGAN

[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

unify-parameter-efficient-tuning

Implementation of paper "Towards a Unified View of Parameter-Efficient Transfer Learning" (ICLR 2022)

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)