# Loading model from\_pretrained with dummy parameter

**URL:** <https://discuss.huggingface.co/t/loading-model-from-pretrained-with-dummy-parameter/36742>\
**Category:** 🤗Transformers\
**Created:** [April 16, 2023, 11:33am UTC](https://discuss.huggingface.co/t/loading-model-from-pretrained-with-dummy-parameter/36742 "2023-04-16T11:33:13Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ndvb](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ndvb/32/17239_2.png) [@ndvb](https://discuss.huggingface.co/u/ndvb)\
**Post date:** [April 16, 2023, 11:33am UTC](https://discuss.huggingface.co/t/loading-model-from-pretrained-with-dummy-parameter/36742/1 "2023-04-16T11:33:13Z")

</div>

I am doing LlamaForCausalLM.from\_pretrained, however, for fast development turnaround, is there a way to pass additional parameter to the from\_pretrained method, to indicate that I just want to create a dummy model in memory, with same structure as the pretrained model (on disk), but just with empty or random weights, in order to increase speed for loading? I don’t care about weights being loaded from disk, just want to load it to memory as soon as possible.