Light

zwhe99 / feedbackmt Goto Github PK

View Code? Open in Web Editor NEW

18.0 1.0 1.0 8.67 MB

Code of "Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model"

Home Page: https://arxiv.org/abs/2401.12873

Dockerfile 0.06% Python 88.84% Shell 11.09%

feedbackmt's Introduction

FeedbackMT

Code of Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model

Environment

conda create -n feedbackmt python=3.10.0
conda activate feedbackmt
cd src/LMFlow
pip3 install -e .
cd ../../
pip3 install -r requirements.txt
conda install mpi4py

Data

Download from Google drive.

unzip data.zip

Training

See training_scripts.

Inference

python3 src/inference_sft.py \
    --model-name-or-path <model path> \
    --inst-file data/instruct_follow.txt \
    --lang-pair en-zh \
    --input-file <input file> \
    --output-file <output file> \
    --search-algorithm beam \
    --batch 2 \
    --seed 0 \
    --model-type s2s \ # --model-type s2s for NLLB; --model-type causal for LLAMA-2
    --beam 4

Critical code

src/LMFlow/src/lmflow/pipeline/raft_aligner.py     # RAFT/RAFT+ for LLAMA2
src/LMFlow/src/lmflow/pipeline/raft_aligner_t2t.py # RAFT/RAFT+ for NLLB
src/LMFlow/src/lmflow/pipeline/mrt_aligner_t2t.py  # MRT/MRT+   for NLLB

Citation

@inproceedings{he2024improving,
    title = "Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model",
    author={Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, Zhaopeng Tu},
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    year = "2024",
    url = "https://aclanthology.org/2024.naacl-long.451",
}

Acknowledgement

OptimalScale/LMFlow: The RAFT implementation is based on LMFlow.
wxjiao/ParroT: Training and inference scripts are based on ParroT

feedbackmt's People

Contributors

Stargazers

Watchers

Forkers

feedbackmt's Issues

Could you help me check your unbabel-comet and huggingface-hub version?

Where are the models or how to train or get these models? model_path=$WS/models/sft-data.wmt20-train+llm.nllb-200-1.3B/checkpoint-5209

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.