Re:Show HN: AI model on a $3 chip (esp32)
by txtai on Thursday February 02, 2023 @05:59PM
(#34634508)
Very interesting! Looking forward to seeing more embedded AI devices coming out.
More NLP based, but here is an article on an effort to build Transformers micromodels to run on embedded devices. The model in this example is under 1MB. Goal would be to ultimately convert this from ONNX to TFLite.
More NLP based, but here is an article on an effort to build Transformers micromodels to run on embedded devices. The model in this example is under 1MB. Goal would be to ultimately convert this from ONNX to TFLite.
https://neuml.hashnode.dev/train-a-language-model-from-scrat...