BitNet icon indicating copy to clipboard operation
BitNet copied to clipboard

Published 20 hours ago • verified publisher icon microsoft

how to generate a dummy modelQwen models

Open summerHearts opened this issue 1 year ago • 2 comments

Traceback (most recent call last): File "/BitNet/utils/generate-dummy-bitnet-model.py", line 1048, in main() File "BitNet/utils/generate-dummy-bitnet-model.py", line 971, in main model_class = Model.from_model_architecture(hparams["architectures"][0]) File "BitNet/utils/generate-dummy-bitnet-model.py", line 312, in from_model_architecture raise NotImplementedError(f'Architecture {arch!r} not supported!') from None NotImplementedError: Architecture 'Qwen2ForCausalLM' not supported! Image

How should I handle it，thanks

summerHearts avatar Oct 21 '24 08:10 summerHearts

Check Compatibility: Ensure that the model architecture you're trying to use is supported in BitNet. Review the model class or BitNet documentation for supported architectures.

Update or Modify: If Qwen2ForCausalLM is not supported, you might need to modify the code to use a supported architecture or contribute by adding support if needed.

masembebrian avatar Oct 21 '24 12:10 masembebrian

assign me this issue.

masembebrian avatar Oct 23 '24 13:10 masembebrian