mii/tokenizers
1
0
Fork 0
mirror of https://github.com/mii443/tokenizers.git synced 2025-08-23 00:35:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Node - Trainers train the Model in-place

Browse Source
This commit is contained in:
Anthony MOI
2020-11-19 19:57:50 -05:00
committed by Anthony MOI
parent 387b8a1033
commit 7fc37a03e8
5 changed files with 69 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
bindings/node/examples/documentation/pipeline.test.ts
View File

@ -94,7 +94,7 @@ describe("pipelineExample", () => {
let { Tokenizer } = require("tokenizers/bindings/tokenizer");
let { WordPiece } = require("tokenizers/bindings/models");
let bertTokenizer = new Tokenizer(WordPiece.empty());
let bertTokenizer = new Tokenizer(WordPiece.init({}, { unkToken: "[UNK]" }));
// END bert_setup_tokenizer
// START bert_setup_normalizer
let { sequenceNormalizer, lowercaseNormalizer, nfdNormalizer, stripAccentsNormalizer }
@ -120,20 +120,13 @@ describe("pipelineExample", () => {
// END bert_setup_processor
// START bert_train_tokenizer
let { wordPieceTrainer } = require("tokenizers/bindings/trainers");
let { promisify } = require("util");
let trainer = wordPieceTrainer({
vocabSize: 30522,
specialTokens: ["[UNK]", "[CLS]", "[SEP]", "[PAD]", "[MASK]"]
});
let files = ["test", "train", "valid"].map(split => `data/wikitext-103-raw/wiki.${split}.raw`);
bertTokenizer.train(trainer, files);
let modelFiles = bertTokenizer.getModel().save("data", "bert-wiki");
let fromFile = promisify(WordPiece.fromFile);
bertTokenizer.setModel(await fromFile(modelFiles[0], {
unkToken: "[UNK]"
}));
bertTokenizer.train(files, trainer);
bertTokenizer.save("data/bert-wiki.json")
// END bert_train_tokenizer