Different LLM instead of the default one

[lakpriya1s]

const pipe = await pipeline('text-generation', 'onnx-community/Llama-3.2-1B-Instruct-q4f16');

How can I use a different LLM instead of the default one? I'm getting below error!

I actually need to run the Llama 3.2 completely locally on an iPhone. Could you help me to do it?

[hans00]

onnx-community/Llama-3.2-1B-Instruct-q4f16 does not provide onnx/model.onnx file.
You should specify the model file name model_q4f16.onnx using model_file_name

const pipe = await pipeline(
  'text-generation',
  'onnx-community/Llama-3.2-1B-Instruct-q4f16',
  { model_file_name: 'model_q4f16.onnx' }
);