# LLM, CNN and SDRs

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-cnn-and-sdrs%2F75577%3E%5C
**Category:** 🤗 Course Projects\
**Created:** [March 2, 2024, 9:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-cnn-and-sdrs%2F75577 "2024-03-02T09:19:07Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![aquahood](https://avatars.discourse-cdn.com/v4/letter/a/aeb1de/32.png) [@aquahood](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Faquahood)%5C
**Post date:** [March 2, 2024, 9:19am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllm-cnn-and-sdrs%2F75577%2F1 "2024-03-02T09:19:07Z")

</div>

I would like to combine a e.e. dataset (I have 400 advanced electrical engineering and radio engineering, and space vehicle engineering textbooks I would like to integrate into a knowledge based), then add all the literature for Gnu radio and Sig54? Sig53 is built on a CNN structure and has a 5 million sample data set over 53 modulation types. It would be the fusion of LLM and CNN with SDRs. Think you could get a multi modal model to output a GNU Radio template based off a sample?