rust-bert/examples/summarization_t5.rs
guillaume-be 540c9268e7
ONNX Support (#346)
* Fixed Clippy warnings

* Revert "Shallow clone optimization (#243)"

This reverts commit ba584653bc.

* updated dependencies

* tryouts

* GPT2 tryouts

* WIP GPT2

* input mapping

* Cache storage

* Initial GPT2 prototype

* Initial ONNX Config and decoder implementation

* ONNXDecoder first draft

* Use Decoders in example

* Automated tch-ort conversion, decoder implementation

* ONNXCausalDecoder implementation

* Refactored _get_var_store to be optional, added get_device to gen trait

* updated example

* Added decoder_start_token_id to ConfigOption

* Addition of ONNXModelConfig, make max_position_embeddigs optional

* Addition of forward pass function for ONNXModel

* Working ONNX causal decoder

* Simplify tensor conversion

* refactor translation to facilitate ONNX integration

* Implementation of ONNXEncoder

* Implementation of ONNXConditionalGenerator

* working ONNXCausalGenerator

* - Reworked model resources type for pipelines and generators

* Aligned ONNXConditionalGenerator with other generators to use GenerateConfig for creation

* Moved force_token_id_generation to common utils function, fixed tests, Translation implementation

* generalized forced_bos and forced_eos tokens generation

* Aligned the `encode_prompt_text` method across language models

* Fix prompt encoding for causal generation

* Fix prompt encoding for causal generation

* Support for ONNX models for SequenceClassification

* Support for ONNX models for TokenClassification

* Support for ONNX models for POS and NER pipelines

* Support for ONNX models for ZeroShotClassification pipeline

* Support for ONNX models for QuestionAnswering pipeline

* Support for ONNX models for MaskedLM pipeline

* Added token_type_ids , updated layer cache i/o parsing for ONNX pipelines

* Support for ONNX models for TextGenerationPipeline, updated examples for remote resources

* Remove ONNX zero-shot classification example (lack of correct pretrained model)

* Addition of tests for ONNX pipelines support

* Made onnx feature optional

* Fix device lookup with onnx feature enabled

* Updates from main branch

* Flexible tokenizer creation for M2M100 (NLLB support), make NLLB test optional du to their size

* Fixed Clippy warnings

* Addition of documentation for ONNX

* Added documentation for ONNX support

* upcoming tch 1.12 fixes

* Fix merge conflicts

* Fix merge conflicts (2)

* Add download libtorch feature to ONNX tests

* Add download-onnx feature

* attempt to enable onnx download

* add remote resources feature

* onnx download

* pin ort version

* Update ort version
2023-05-30 07:20:25 +01:00

64 lines
4.1 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// Copyright 2019-present, the HuggingFace Inc. team, The Google AI Language Team and Facebook, Inc.
// Copyright 2019 Guillaume Becquin
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
extern crate anyhow;
use rust_bert::pipelines::common::{ModelResource, ModelType};
use rust_bert::pipelines::summarization::{SummarizationConfig, SummarizationModel};
use rust_bert::resources::RemoteResource;
use rust_bert::t5::{T5ConfigResources, T5ModelResources, T5VocabResources};
fn main() -> anyhow::Result<()> {
let config_resource = RemoteResource::from_pretrained(T5ConfigResources::T5_SMALL);
let vocab_resource = RemoteResource::from_pretrained(T5VocabResources::T5_SMALL);
let weights_resource = RemoteResource::from_pretrained(T5ModelResources::T5_SMALL);
let summarization_config = SummarizationConfig::new(
ModelType::T5,
ModelResource::Torch(Box::new(weights_resource)),
config_resource,
vocab_resource,
None,
);
let summarization_model = SummarizationModel::new(summarization_config)?;
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 HarvardSmithsonian 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."];
// Credits: WikiNews, CC BY 2.5 license (https://en.wikinews.org/wiki/Astronomers_find_water_vapour_in_atmosphere_of_exoplanet_K2-18b)
let _output = summarization_model.summarize(&input);
for sentence in _output {
println!("{sentence}");
}
Ok(())
}