npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

deep-chat-web-llm

v0.0.27

Published

Hardware accelerated language model chats on browsers

Downloads

93

Readme

Web LLM

| NPM Package | Get Started | Examples | Documentation | MLC LLM | Discord |

WebLLM is a modular, customizable javascript package that directly brings language model chats directly onto web browsers with hardware acceleration. Everything runs inside the browser with no server support and is accelerated with WebGPU. We can bring a lot of fun opportunities to build AI assistants for everyone and enable privacy while enjoying GPU acceleration.

Check out our demo webpage to try out! You can use WebLLM as a base npm package and build your own web application on top of it by following the documentation and checking out Get Started. This project is a companion project of MLC LLM, which runs LLMs natively on iPhone and other native local environments.

Get Started

WebLLM offers a minimalist and modular interface to access the chatbot in the browser. The WebLLM package itself does not come with UI, and is designed in a modular way to hook to any of the UI components. The following code snippet demonstrate a simple example that generates a streaming response on a webpage. You can check out examples/get-started to see the complete example.

import * as webllm from "@mlc-ai/web-llm";

// We use label to intentionally keep it simple
function setLabel(id: string, text: string) {
  const label = document.getElementById(id);
  if (label == null) {
    throw Error("Cannot find label " + id);
  }
  label.innerText = text;
}

async function main() {
  // create a ChatModule,
  const chat = new webllm.ChatModule();
  // This callback allows us to report initialization progress
  chat.setInitProgressCallback((report: webllm.InitProgressReport) => {
    setLabel("init-label", report.text);
  });
  // You can also try out "RedPajama-INCITE-Chat-3B-v1-q4f32_1"
  await chat.reload("Llama-2-7b-chat-hf-q4f32_1");

  const generateProgressCallback = (_step: number, message: string) => {
    setLabel("generate-label", message);
  };

  const prompt0 = "What is the capital of Canada?";
  setLabel("prompt-label", prompt0);
  const reply0 = await chat.generate(prompt0, generateProgressCallback);
  console.log(reply0);

  const prompt1 = "Can you write a poem about it?";
  setLabel("prompt-label", prompt1);
  const reply1 = await chat.generate(prompt1, generateProgressCallback);
  console.log(reply1);

  console.log(await chat.runtimeStatsText());
}

main();

Using Web Worker

WebLLM comes with API support for WebWorker so you can hook the generation process into a separate worker thread so that the compute in the webworker won't disrupt the UI.

We first create a worker script that created a ChatModule and hook it up to a handler that handles requests.

// worker.ts
import { ChatWorkerHandler, ChatModule } from "@mlc-ai/web-llm";

// Hookup a chat module to a worker handler
const chat = new ChatModule();
const handler = new ChatWorkerHandler(chat);
self.onmessage = (msg: MessageEvent) => {
  handler.onmessage(msg);
};

Then in the main logic, we create a ChatWorkerClient that implements the same ChatInterface. The rest of the logic remains the same.

// main.ts
import * as webllm from "@mlc-ai/web-llm";

async function main() {
  // Use a chat worker client instead of ChatModule here
  const chat = new webllm.ChatWorkerClient(new Worker(
    new URL('./worker.ts', import.meta.url),
    {type: 'module'}
  ));
  // everything else remains the same
}

Build a ChatApp

You can find a complete a complete chat app example in examples/simple-chat.

Customized Model Weights

WebLLM works as a companion project of MLC LLM. It reuses the model artifact and builds flow of MLC LLM, please check out MLC LLM document on how to add new model weights and libraries to WebLLM.

Here, we go over the high-level idea. There are two elements of the WebLLM package that enables new models and weight variants.

  • model_url: Contains a URL to model artifacts, such as weights and meta-data.
  • model_lib_url: A URL to the web assembly library (i.e. wasm file) that contains the executables to accelerate the model computations.

Both are customizable in the WebLLM.

async main() {
  const myLlamaUrl = "/url/to/my/llama";
  const appConfig = {
    "model_list": [
      {
        "model_url": myLlamaUrl,
        "local_id": "MyLlama-3b-v1-q4f32_0"
        "model_lib_url": "/url/to/myllama3b.wasm",
      }
    ],
  };
  // override default
  const chatOpts = {
    "repetition_penalty": 1.01
  };

  const chat = new ChatModule();
  // load a prebuilt model
  // with a chat option override and app config
  // under the hood, it will load the model from myLlamaUrl
  // and cache it in the browser cache
  // The chat will also load the model library from "/url/to/myllama3b.wasm",
  // assuming that it is compatible to the model in myLlamaUrl.
  await chat.reload("MyLlama-3b-v1-q4f32_0", chatOpts, appConfig);
}

In many cases, we only want to supply the model weight variant, but not necessarily a new model (e.g. NeuralHermes-Mistral can reuse Mistral's model library; WizardMath can reuse Llama-2's model library). For an example of how a model library is shared by different model variants, see examples/simple-chat/src/gh-config.js. We also provide a plethora of prebuilt model libraries, including:

  • Llama-2-7b-chat-hf-q4f32_1: Llama-7b models.
  • RedPajama-INCITE-Chat-3B-v1-q4f32_1: RedPajama-3B variants.
  • Mistral-7B-Instruct-v0.1-q4f16_1: Mistral-7B variants.
  • and many more at binary-mlc-llm-libs.

Use WebLLM Package

You can directly use WebLLM in your package via npm. Checkout instructions in the following project

Build WebLLM Package From Source

NOTE: you don't need to build by yourself unless you would like to change the WebLLM package, follow use WebLLM instead.

WebLLM package is a web runtime designed for MLC LLM.

  1. Install all the prerequisites for compilation:

    1. emscripten. It is an LLVM-based compiler that compiles C/C++ source code to WebAssembly.
      • Follow the installation instruction to install the latest emsdk.
      • Source emsdk_env.sh by source path/to/emsdk_env.sh, so that emcc is reachable from PATH and the command emcc works.
    2. Install jekyll by following the official guides. It is the package we use for website. This is not needed if you're using nextjs (see next-simple-chat in the examples).
    3. Install jekyll-remote-theme by command. Try gem mirror if install blocked.
      gem install jekyll-remote-theme

    We can verify the successful installation by trying out emcc and jekyll in terminal, respectively.

  2. Setup necessary environment

    Prepare all the necessary dependencies for web build:

    ./scripts/prep_deps.sh
  3. Buld WebLLM Package

    npm run build
  4. Validate some of the sub-packages

    You can then go to the subfolders in examples to validate some of the sub-packages. We use Parcelv2 for bundling. Although Parcel is not very good at tracking parent directory changes sometimes. When you make a change in the WebLLM package, try to edit the package.json of the subfolder and save it, which will trigger Parcel to rebuild.

Links

Acknowledgement

This project is initiated by members from CMU catalyst, UW SAMPL, SJTU, OctoML and the MLC community. We would love to continue developing and supporting the open-source ML community.

This project is only possible thanks to the shoulders open-source ecosystems that we stand on. We want to thank the Apache TVM community and developers of the TVM Unity effort. The open-source ML community members made these models publicly available. PyTorch and Hugging Face communities make these models accessible. We would like to thank the teams behind vicuna, SentencePiece, LLaMA, Alpaca. We also would like to thank the WebAssembly, Emscripten, and WebGPU communities. Finally, thanks to Dawn and WebGPU developers.