onnx-community

/

gpt-oss-20b-ONNX

like 11

Follow

ONNX Community 1.85k

Hello,

I tried to use this model like so:

import { pipeline } from "https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.0.0-next.2";

const generator = await pipeline(
  "text-generation",
  "onnx-community/gpt-oss-20b-ONNX",
  {
    dtype: "q4f16",
    device: "webgpu"
  },
);

const messages = [
    {
      role: "user",
      content: "Who are you?",
    }
];

const output = await generator(messages);

console.log(output[0].generated_text.at(-1).content);

But I almost always get a blank response or a weird output. Am I missing something in order to run this model?

Any assistance will be appreciated!