rust-bert 0.5.3

Ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
Documentation 
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81

// 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 failure;
extern crate dirs;

use std::path::PathBuf;
use tch::{Device, nn, Tensor};
use rust_tokenizers::{TruncationStrategy, Tokenizer, Gpt2Tokenizer};
use failure::err_msg;
use rust_bert::Config;
use rust_bert::gpt2::{Gpt2Config, GPT2LMHeadModel, LMHeadModel};


fn main() -> failure::Fallible<()> {
    //    Resources paths
    let mut home: PathBuf = dirs::home_dir().unwrap();
    home.push("rustbert");
    home.push("gpt2");
    let config_path = &home.as_path().join("config.json");
    let vocab_path = &home.as_path().join("vocab.txt");
    let merges_path = &home.as_path().join("merges.txt");
    let weights_path = &home.as_path().join("model.ot");

    if !config_path.is_file() | !vocab_path.is_file() | !merges_path.is_file() | !weights_path.is_file() {
        return Err(
            err_msg("Could not find required resources to run example. \
                          Please run ../utils/download_dependencies_gpt2.py \
                          in a Python environment with dependencies listed in ../requirements.txt"));
    }

//    Set-up masked LM model
    let device = Device::Cpu;
    let mut vs = nn::VarStore::new(device);
    let tokenizer: Gpt2Tokenizer = Gpt2Tokenizer::from_file(vocab_path.to_str().unwrap(), merges_path.to_str().unwrap(), false);
    let config = Gpt2Config::from_file(config_path);
    let gpt2_model = GPT2LMHeadModel::new(&vs.root(), &config);
    vs.load(weights_path)?;

//    Define input
    let input = ["One two three four five six seven eight nine ten eleven"];
    let tokenized_input = tokenizer.encode_list(input.to_vec(), 128, &TruncationStrategy::LongestFirst, 0);
    let max_len = tokenized_input.iter().map(|input| input.token_ids.len()).max().unwrap();
    let tokenized_input = tokenized_input.
        iter().
        map(|input| input.token_ids.clone()).
        map(|mut input| {
            input.extend(vec![0; max_len - input.len()]);
            input
        }).
        map(|input|
            Tensor::of_slice(&(input))).
        collect::<Vec<_>>();
    let input_tensor = Tensor::stack(tokenized_input.as_slice(), 0).to(device);

//    Forward pass
    let (output, _, _, _) = gpt2_model.forward_t(
        &Some(input_tensor),
        &None,
        &None,
        &None,
        &None,
        &None,
        false).unwrap();

    let next_word_id = output.get(0).get(-1).argmax(-1, true).int64_value(&[0]);
    let next_word = tokenizer.decode(vec!(next_word_id), true, true);
    println!("Provided input: {}", input[0]);
    println!("Next word: {}", next_word);

    Ok(())
}