#nlp #deep-learning #machine-learning #translation #transformers

bin+lib rust-bert

Ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,…)

37 releases (13 breaking)

0.14.0 Feb 23, 2021
0.12.1 Jan 4, 2021
0.12.0 Nov 29, 2020
0.7.11 Jul 26, 2020
0.5.3 Mar 27, 2020

#1 in Machine learning

Download history 67/week @ 2020-12-19 61/week @ 2020-12-26 357/week @ 2021-01-02 96/week @ 2021-01-09 114/week @ 2021-01-16 93/week @ 2021-01-23 82/week @ 2021-01-30 92/week @ 2021-02-06 203/week @ 2021-02-13 164/week @ 2021-02-20 178/week @ 2021-02-27 178/week @ 2021-03-06 57/week @ 2021-03-13 129/week @ 2021-03-20 173/week @ 2021-03-27 205/week @ 2021-04-03

593 downloads per month
Used in 2 crates


27K SLoC


Build Status Latest version Documentation License

Rust native Transformer-based models implementation. Port of Huggingface's Transformers library, using the tch-rs crate and pre-processing from rust-tokenizers. Supports multithreaded tokenization and GPU inference. This repository exposes the model base architecture, task-specific heads (see below) and ready-to-use pipelines. Benchmarks are available at the end of this document.

The following models are currently implemented:

Sequence classification Token classification Question answering Text Generation Summarization Translation Masked LM

Ready-to-use pipelines

Based on Huggingface's pipelines, ready to use end-to-end NLP pipelines are available as part of this crate. The following capabilities are currently available:

Disclaimer The contributors of this repository are not responsible for any generation from the 3rd party utilization of the pretrained systems proposed herein.

1. Question Answering

Extractive question answering from a given question and context. DistilBERT model finetuned on SQuAD (Stanford Question Answering Dataset)

    let qa_model = QuestionAnsweringModel::new(Default::default())?;
    let question = String::from("Where does Amy live ?");
    let context = String::from("Amy lives in Amsterdam");

    let answers = qa_model.predict(&vec!(QaInput { question, context }), 1, 32);


[Answer { score: 0.9976814985275269, start: 13, end: 21, answer: "Amsterdam" }]

2. Translation

Translation using the MarianMT architecture and pre-trained models from the Opus-MT team from Language Technology at the University of Helsinki. Currently supported languages are :

  • English <-> French
  • English <-> Spanish
  • English <-> Portuguese
  • English <-> Italian
  • English <-> Catalan
  • English <-> German
  • English <-> Russian
  • French <-> German
    let translation_config = TranslationConfig::new(Language::EnglishToFrench, Device::cuda_if_available());
    let mut model = TranslationModel::new(translation_config)?;
    let input = ["This is a sentence to be translated"];
    let output = model.translate(&input);


Il s'agit d'une phrase à traduire

3. Summarization

Abstractive summarization using a pretrained BART model.

    let summarization_model = SummarizationModel::new(Default::default())?;
    let input = ["In findings published Tuesday in Cornell University's arXiv by a team of scientists \
from the University of Montreal and a separate report published Wednesday in Nature Astronomy by a team \
from University College London (UCL), the presence of water vapour was confirmed in the atmosphere of K2-18b, \
a planet circling a star in the constellation Leo. This is the first such discovery in a planet in its star's \
habitable zone — not too hot and not too cold for liquid water to exist. The Montreal team, led by Björn Benneke, \
used data from the NASA's Hubble telescope to assess changes in the light coming from K2-18b's star as the planet \
passed between it and Earth. They found that certain wavelengths of light, which are usually absorbed by water, \
weakened when the planet was in the way, indicating not only does K2-18b have an atmosphere, but the atmosphere \
contains water in vapour form. The team from UCL then analyzed the Montreal team's data using their own software \
and confirmed their conclusion. This was not the first time scientists have found signs of water on an exoplanet, \
but previous discoveries were made on planets with high temperatures or other pronounced differences from Earth. \
\"This is the first potentially habitable planet where the temperature is right and where we now know there is water,\" \
said UCL astronomer Angelos Tsiaras. \"It's the best candidate for habitability right now.\" \"It's a good sign\", \
said Ryan Cloutier of the Harvard–Smithsonian Center for Astrophysics, who was not one of either study's authors. \
\"Overall,\" he continued, \"the presence of water in its atmosphere certainly improves the prospect of K2-18b being \
a potentially habitable planet, but further observations will be required to say for sure. \"
K2-18b was first identified in 2015 by the Kepler space telescope. It is about 110 light-years from Earth and larger \
but less dense. Its star, a red dwarf, is cooler than the Sun, but the planet's orbit is much closer, such that a year \
on K2-18b lasts 33 Earth days. According to The Guardian, astronomers were optimistic that NASA's James Webb space \
telescope — scheduled for launch in 2021 — and the European Space Agency's 2028 ARIEL program, could reveal more \
about exoplanets like K2-18b."];

    let output = summarization_model.summarize(&input);

(example from: WikiNews)


"Scientists have found water vapour on K2-18b, a planet 110 light-years from Earth. 
This is the first such discovery in a planet in its star's habitable zone. 
The planet is not too hot and not too cold for liquid water to exist."

4. Dialogue Model

Conversation model based on Microsoft's DialoGPT. This pipeline allows the generation of single or multi-turn conversations between a human and a model. The DialoGPT's page states that

The human evaluation results indicate that the response generated from DialoGPT is comparable to human response quality under a single-turn conversation Turing test. (DialoGPT repository)

The model uses a ConversationManager to keep track of active conversations and generate responses to them.

use rust_bert::pipelines::conversation::{ConversationModel, ConversationManager};

let conversation_model = ConversationModel::new(Default::default());
let mut conversation_manager = ConversationManager::new();

let conversation_id = conversation_manager.create("Going to the movies tonight - any suggestions?");
let output = conversation_model.generate_responses(&mut conversation_manager);

Example output:

"The Big Lebowski."

5. Natural Language Generation

Generate language based on a prompt. GPT2 and GPT available as base models. Include techniques such as beam search, top-k and nucleus sampling, temperature setting and repetition penalty. Supports batch generation of sentences from several prompts. Sequences will be left-padded with the model's padding token if present, the unknown token otherwise. This may impact the results and it is recommended to submit prompts of similar length for best results

    let model = GPT2Generator::new(Default::default())?;
    let input_context_1 = "The dog";
    let input_context_2 = "The cat was";

    let output = model.generate(Some(vec!(input_context_1, input_context_2)), 0, 30, true, false, 
                                5, 1.2, 0, 0.9, 1.0, 1.0, 3, 3, None);

Example output:

    "The dog's owners, however, did not want to be named. According to the lawsuit, the animal's owner, a 29-year"
    "The dog has always been part of the family. \"He was always going to be my dog and he was always looking out for me"
    "The dog has been able to stay in the home for more than three months now. \"It's a very good dog. She's"
    "The cat was discovered earlier this month in the home of a relative of the deceased. The cat\'s owner, who wished to remain anonymous,"
    "The cat was pulled from the street by two-year-old Jazmine.\"I didn't know what to do,\" she said"
    "The cat was attacked by two stray dogs and was taken to a hospital. Two other cats were also injured in the attack and are being treated."

6. Zero-shot classification

Performs zero-shot classification on input sentences with provided labels using a model fine-tuned for Natural Language Inference.

    let sequence_classification_model = ZeroShotClassificationModel::new(Default::default())?;

    let input_sentence = "Who are you voting for in 2020?";
    let input_sequence_2 = "The prime minister has announced a stimulus package which was widely criticized by the opposition.";
    let candidate_labels = &["politics", "public health", "economics", "sports"];

    let output = sequence_classification_model.predict_multilabel(
        &[input_sentence, input_sequence_2],


  [ Label { "politics", score: 0.972 }, Label { "public health", score: 0.032 }, Label {"economics", score: 0.006 }, Label {"sports", score: 0.004 } ],
  [ Label { "politics", score: 0.975 }, Label { "public health", score: 0.0818 }, Label {"economics", score: 0.852 }, Label {"sports", score: 0.001 } ],

7. Sentiment analysis

Predicts the binary sentiment for a sentence. DistilBERT model finetuned on SST-2.

    let sentiment_classifier = SentimentModel::new(Default::default())?;
    let input = [
        "Probably my all-time favorite movie, a story of selflessness, sacrifice and dedication to a noble cause, but it's not preachy or boring.",
        "This film tried to be too many things all at once: stinging political satire, Hollywood blockbuster, sappy romantic comedy, family values promo...",
        "If you like original gut wrenching laughter you will like this movie. If you are young or old then you will love this movie, hell even my mom liked it.",

    let output = sentiment_classifier.predict(&input);

(Example courtesy of IMDb)


    Sentiment { polarity: Positive, score: 0.9981985493795946 },
    Sentiment { polarity: Negative, score: 0.9927982091903687 },
    Sentiment { polarity: Positive, score: 0.9997248985164333 }

8. Named Entity Recognition

Extracts entities (Person, Location, Organization, Miscellaneous) from text. BERT cased large model finetuned on CoNNL03, contributed by the MDZ Digital Library team at the Bavarian State Library. Models are currently available for English, German, Spanish and Dutch.

    let ner_model = NERModel::new(default::default())?;

    let input = [
        "My name is Amy. I live in Paris.",
        "Paris is a city in France."
    let output = ner_model.predict(&input);


    Entity { word: "Amy", score: 0.9986, label: "I-PER" }
    Entity { word: "Paris", score: 0.9985, label: "I-LOC" }
    Entity { word: "Paris", score: 0.9988, label: "I-LOC" }
    Entity { word: "France", score: 0.9993, label: "I-LOC" }


For simple pipelines (sequence classification, tokens classification, question answering) the performance between Python and Rust is expected to be comparable. This is because the most expensive part of these pipeline is the language model itself, sharing a common implementation in the Torch backend. The End-to-end NLP Pipelines in Rust provides a benchmarks section covering all pipelines.

For text generation tasks (summarization, translation, conversation, free text generation), significant benefits can be expected (up to 2 to 4 times faster processing depending on the input and application). The article Accelerating text generation with Rust focuses on these text generation applications and provides more details on the performance comparison to Python.

Base models

The base model and task-specific heads are also available for users looking to expose their own transformer based models. Examples on how to prepare the date using a native tokenizers Rust library are available in ./examples for BERT, DistilBERT, RoBERTa, GPT, GPT2 and BART. Note that when importing models from Pytorch, the convention for parameters naming needs to be aligned with the Rust schema. Loading of the pre-trained weights will fail if any of the model parameters weights cannot be found in the weight files. If this quality check is to be skipped, an alternative method load_partial can be invoked from the variables store.


A number of pretrained model configuration, weights and vocabulary are downloaded directly from Huggingface's model repository. The list of models available with Rust-compatible weights is available at https://huggingface.co/models?filter=rust. The models will be downloaded to the environment variable RUSTBERT_CACHE if it exists, otherwise to ~/.cache/.rustbert. Additional models can be added if of interest, please raise an issue.

In order to load custom weights to the library, these need to be converter to a binary format that can be read by Libtorch (the original .bin files are pickles and cannot be used directly). Several Python scripts to load Pytorch weights and convert them to the appropriate format are provided and can be adapted based on the model needs.

  1. Compile the package: cargo build
  2. Download the model files & perform necessary conversions
    • Set-up a virtual environment and install dependencies
    • Download the Pytorch model of interest (pytorch_model.bin from Huggingface's model repository)
    • run the conversion script python /utils/convert_model.py <PATH_TO_PYTORCH_WEIGHTS>.


If you use rust-bert for your work, please cite End-to-end NLP Pipelines in Rust:

    title = "End-to-end {NLP} Pipelines in Rust",
    author = "Becquin, Guillaume",
    booktitle = "Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.nlposs-1.4",
    pages = "20--25",


Thank you to Hugging Face for hosting a set of weights compatible with this Rust library. The list of ready-to-use pretrained models is listed at https://huggingface.co/models?filter=rust.


~480K SLoC