此内容尚未提供您的语言版本,正在以英文显示。

Transformers Js

插件已验证活跃

Run state-of-the-art machine learning models directly in JavaScript/TypeScript for NLP, computer vision, audio processing, and multimodal tasks. Works in Node.js and browsers with WebGPU/WASM using Hugging Face models.

目的

To empower JavaScript/TypeScript developers to integrate powerful machine learning capabilities into their applications without needing a separate Python backend or ML server.

功能

Run ML models directly in JS/TS
Supports NLP, computer vision, audio, and multimodal tasks
Works in Node.js, browsers, Bun, and Deno
Leverages WebGPU/WASM for acceleration
Uses Hugging Face Hub models

使用场景

Adding ML features to web applications
Client-side AI processing for privacy and speed
Prototyping ML workflows in JavaScript
Building multimodal AI applications

非目标

Providing a Python-based ML server
Requiring a separate backend for model inference
Replacing native ML frameworks on their respective platforms

Execution

info:Pinned dependenciesWhile the SKILL.md mentions NPM installation, it does not explicitly detail if dependencies are pinned via a lockfile for the extension's own scripts.

Invocation

info:Name collisionsThe skill 'transformers-js' is distinct and does not appear to collide with Claude Code built-ins or other provided Hugging Face skills.

安装

请先添加 Marketplace

/plugin marketplace add huggingface/skills

/plugin install transformers-js@huggingface-skills

质量评分

已验证

96 /100

1 day ago 分析

信任信号

最近提交2 days ago

GitHub 所有者 huggingface

星标10.5k

许可证Apache-2.0

网站huggingface.co

状态

查看源代码

类似扩展

Train Sentence Transformers

Train or fine-tune sentence-transformers models across all three architectures: SentenceTransformer (bi-encoder embeddings), CrossEncoder (rerankers), and SparseEncoder (SPLADE). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing.

插件

huggingface

Autoresearch Agent

100

Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).

插件

alirezarezvani