1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
//! # Marian
//!
//! Implementation of the Marian language model ([Marian: Fast Neural Machine Translation in {C++}](http://www.aclweb.org/anthology/P18-4020) Junczys-Dowmunt, Grundkiewicz, Dwojak, Hoang, Heafield, Neckermann, Seide, Germann, Fikri Aji, Bogoychev, Martins, Birch, 2018).
//! The base model is implemented in the `bart::BartModel` struct. This model includes a language model head: `marian::MarianForConditionalGeneration`
//! implementing the common `generation::LMHeadModel` trait shared between the models used for generation (see `pipelines` for more information).
//!
//! # Model set-up and pre-trained weights loading
//!
//! A full working example is provided in `examples/translation.rs`, run with `cargo run --example translation`.
//! All models expect the following resources:
//! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
//! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
//! - `MarianTokenizer` using a `vocab.json` vocabulary and `spiece.model` sentence piece model
//!
//! Pretrained models for a number of language pairs are available and can be downloaded using RemoteResources. These are shared under Creative Commons Attribution 4.0 International License license by the Opus-MT team from Language Technology at the University of Helsinki at https://github.com/Helsinki-NLP/Opus-MT.
//!
//! ```no_run
//! # fn main() -> failure::Fallible<()> {
//! #
//! use tch::{nn, Device};
//! # use std::path::PathBuf;
//! use rust_bert::bart::{BartConfig, BartModel};
//! use rust_bert::marian::MarianForConditionalGeneration;
//! use rust_bert::resources::{download_resource, LocalResource, Resource};
//! use rust_bert::Config;
//! use rust_tokenizers::preprocessing::tokenizer::marian_tokenizer::MarianTokenizer;
//!
//! let config_resource = Resource::Local(LocalResource {
//! local_path: PathBuf::from("path/to/config.json"),
//! });
//! let vocab_resource = Resource::Local(LocalResource {
//! local_path: PathBuf::from("path/to/vocab.json"),
//! });
//! let sentence_piece_resource = Resource::Local(LocalResource {
//! local_path: PathBuf::from("path/to/spiece.model"),
//! });
//! let weights_resource = Resource::Local(LocalResource {
//! local_path: PathBuf::from("path/to/model.ot"),
//! });
//! let config_path = download_resource(&config_resource)?;
//! let vocab_path = download_resource(&vocab_resource)?;
//! let spiece_path = download_resource(&sentence_piece_resource)?;
//! let weights_path = download_resource(&weights_resource)?;
//!
//! let device = Device::cuda_if_available();
//! let mut vs = nn::VarStore::new(device);
//! let tokenizer = MarianTokenizer::from_files(
//! vocab_path.to_str().unwrap(),
//! spiece_path.to_str().unwrap(),
//! true,
//! );
//! let config = BartConfig::from_file(config_path);
//! let marian_model = MarianForConditionalGeneration::new(&vs.root(), &config, false);
//! vs.load(weights_path)?;
//!
//! # Ok(())
//! # }
//! ```
pub use ;