transformers-js
Codex curated Hugging Face skill for Transformers.js browser or Node inference, model conversion constraints, pipelines, and web deployment.
来源信息
- 仓库
- Rycen7822/skill-retrieval-mcp
- 最近来源活动
- 2026年5月10日 17:34
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 2
- 分支
- 0
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- transformers-js
- description
- Codex curated Hugging Face skill for Transformers.js browser or Node inference, model conversion constraints, pipelines, and web deployment.
- tags
- ["codex-builtin","huggingface","transformers-js","javascript","inference"]
# transformers-js
## When to Use
Use for JavaScript or browser-side inference with Transformers.js, ONNX/web constraints, pipeline setup, and web app integration.
## Do Not Use When
Do not use for Python-only trainer code or Hugging Face Jobs management.
## Required Inputs
Runtime target, model id, task pipeline, bundler or Node version, and browser performance constraints.
## Workflow
1. Select a compatible Transformers.js pipeline.
2. Wire model loading and inference.
3. Handle caching and bundle constraints.
4. Smoke test in browser or Node.
在 GitHub 查看