web-transformers - GitLite

KO | EN

gitlite — search

#javascript #hacktoberfest #ai #go #linux #docker #nodejs #macos #java #windows #awesome #cli #security #open-source

web-transformers

(★ 90)

Transformer neural networks in the browser

파일 탐색기

최종 버전 다운로드 (.zip)

- config.yml
- - favicon512x512-npm.png
  - favicon512x512-npm.svg
  - figma-badge.png
- - build.yml
  - delete-workflow-runs.yml
  - npm-publish.yml
- dependabot.yml
- tasks.json
- - _app.tsx
  - index.tsx
- - favicon.ico
  - vercel.svg
- - globals.css
  - Home.module.css
- .gitignore
- download_models.sh
- next.config.js
- package-lock.json
- package.json
- README.md
- tsconfig.json
- worker.ts
- - make_tests.py
  - t5-base-tests.json
  - t5-base-tokenizer.json
  - tokenizers.test.ts
  - transformers.test.ts
- - AutoTokenizer.ts
  - CharTrie.ts
  - Tokenizer.ts
  - TokenLattice.ts
  - TokenProcessor.ts
- - AutoModelForSeq2SeqLM.ts
  - GenerateOptions.ts
  - NamedTensor.ts
  - PretrainedModel.ts
  - Seq2SeqLMOutput.ts
  - T5ForConditionalGeneration.ts
- index.ts
.eslintignore
.eslintrc
.gitignore
.gitpod.yml
.prettierrc
jest.config.js
LICENSE.md
package-lock.json
package.json
README.md
renovate.json
tsconfig.json

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/praeclarum/web-transformers

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd web-transformers

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Node.js

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Node.js npm 명령어를 쓰려면 Node.js가 설치되어 있어야 합니다. LTS(장기지원) 버전을 추천합니다.

npm i

이 명령어를 터미널에 그대로 입력해 실행하세요.

npm run download_models

이 명령어를 터미널에 그대로 입력해 실행하세요.

npm run dev

개발/실행 서버를 켭니다.

✅ 명령어 실행 후 터미널에 나타나는 주소(보통 http://localhost:3000 형태)를 브라우저에서 열어보세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# web-transformers

[![Build and Test](https://github.com/praeclarum/web-transformers/actions/workflows/build.yml/badge.svg?branch=main)](https://github.com/praeclarum/web-transformers/actions/workflows/build.yml)

This library enables you to run huggingface transformer models directly in the browser.
It accomplishes this by running the models using the
[ONNX Runtime JavaScript API](https://github.com/microsoft/onnxruntime/tree/main/js)
and by implementing its own JavaScript-only tokenization library.

At the moment, it is compatible with Google's T5 models, but it was designed to be expanded.
I hope to support GPT2, Roberta, and InCoder in the future.

## Usage

The following example code shows how to load a tokenizer and a transformer model.
It then uses those objects to create a `generate` functions which generates
output text from input text.

```typescript
import { AutoTokenizer, T5ForConditionalGeneration } from 'web-transformers';

// Load the tokenizer and model
const tokenizer = AutoTokenizer.fromPretrained(modelId, modelsPath);
const model = new T5ForConditionalGeneration(modelId, modelsPath);

// Generate text using Seq2Seq
async function generate(inputText: string) {
    // Tokenize the text
    const inputTokenIds = await tokenizer.encode(inputText);
    // Generate output
    const generationOptions = {
        "maxLength": 50,
        "topK": 10,
    };
    const outputTokenIds = await model.generate(inputTokenIds, generationOptions);
    // Convert output tokens into text
    const outputText = await tokenizer.decode(finalOutputTokenIds, true);
    return outputText;
};

// Translate
console.log(await generate("translate English to French: Hello World!"));
```

## Sample Web App

This repo contains a [sample nextjs app](sample) that translates text using a transformer neural network.

First build the library:

```bash
git clone git@github.com:praeclarum/web-transformers.git
cd web-transformers
npm i
```

Now, build the sample:

```bash
cd sample
npm i
```

Before running the sample, you need to download the model files that will be executed. You can do this by running the following command:

```bash
npm run download_models
```

Then you can run the sample with:

```bash
npm run dev
```

## Models

Currently only the *T5* network is supported.

### Sampling

The neural network outputs the logarithm of the probability of each token.
In order to get a token, a probabilistic sample has to be taken.
The following algorithms are implemented:

* *Greedy*: Take the token with the highest probability.
* *Top-k*: Take the top-k tokens with the highest probability.

## Sponsorship

This library was made possible thanks to the financial support of [Reflect](https://reflect.app). Thanks Reflect!

## License

Copyright © 2022 [Frank A. Krueger](https://github.com/praeclarum). This project is [MIT](LICENSE.md) licensed.