Felladrin/mlc-q4f16-Llama3-ChatQA-1.5-8B

MLC version of nvidia/Llama3-ChatQA-1.5-8B, using q4f16_1 quantization.

Usage

import { CreateMLCEngine } from "@mlc-ai/web-llm";

async main() {
  const appConfig = {
    "model_list": [
      {
        "model": "https://huggingface.co/Felladrin/mlc-q4f16-Llama3-ChatQA-1.5-8B",
        "model_id": "mlc-q4f16-Llama3-ChatQA-1.5-8B"
        "model_lib": "https://huggingface.co/Felladrin/mlc-q4f16-Llama3-ChatQA-1.5-8B/resolve/main/model.wasm",
      }
    ],
  };

  const engine = await CreateMLCEngine(
    "mlc-q4f16-Llama3-ChatQA-1.5-8B",
    { appConfig },
  );
}