mirror of
https://github.com/guillaume-be/rust-bert.git
synced 2024-10-05 16:47:24 +03:00
540c9268e7
* 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
57 lines
2.4 KiB
Rust
57 lines
2.4 KiB
Rust
// Copyright 2021 The Fairseq Authors and The HuggingFace Inc. team. All rights reserved.
|
|
// 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::m2m_100::{
|
|
M2M100ConfigResources, M2M100MergesResources, M2M100ModelResources, M2M100SourceLanguages,
|
|
M2M100TargetLanguages, M2M100VocabResources,
|
|
};
|
|
use rust_bert::pipelines::common::{ModelResource, ModelType};
|
|
use rust_bert::pipelines::translation::{Language, TranslationConfig, TranslationModel};
|
|
use rust_bert::resources::RemoteResource;
|
|
use tch::Device;
|
|
|
|
fn main() -> anyhow::Result<()> {
|
|
let model_resource = RemoteResource::from_pretrained(M2M100ModelResources::M2M100_418M);
|
|
let config_resource = RemoteResource::from_pretrained(M2M100ConfigResources::M2M100_418M);
|
|
let vocab_resource = RemoteResource::from_pretrained(M2M100VocabResources::M2M100_418M);
|
|
let merges_resource = RemoteResource::from_pretrained(M2M100MergesResources::M2M100_418M);
|
|
|
|
let source_languages = M2M100SourceLanguages::M2M100_418M;
|
|
let target_languages = M2M100TargetLanguages::M2M100_418M;
|
|
|
|
let translation_config = TranslationConfig::new(
|
|
ModelType::M2M100,
|
|
ModelResource::Torch(Box::new(model_resource)),
|
|
config_resource,
|
|
vocab_resource,
|
|
Some(merges_resource),
|
|
source_languages,
|
|
target_languages,
|
|
Device::cuda_if_available(),
|
|
);
|
|
let model = TranslationModel::new(translation_config)?;
|
|
|
|
let source_sentence = "This sentence will be translated in multiple languages.";
|
|
|
|
let mut outputs = Vec::new();
|
|
outputs.extend(model.translate(&[source_sentence], Language::English, Language::French)?);
|
|
outputs.extend(model.translate(&[source_sentence], Language::English, Language::Spanish)?);
|
|
outputs.extend(model.translate(&[source_sentence], Language::English, Language::Hindi)?);
|
|
|
|
for sentence in outputs {
|
|
println!("{sentence}");
|
|
}
|
|
Ok(())
|
|
}
|