Tian Lin

Hi @AnastGerus , For LSTM conversion, there is an [article](https://www.tensorflow.org/lite/convert/rnn) and colab describing the process, and you can follow the [colab inside that](https://colab.sandbox.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/examples/experimental_new_converter/Keras_LSTM_fusion_Codelab.ipynb) to do it. For [4 kinds of...

For the limitation 1, it is because the latent variable is turned into constants, and cannot handle control flow correctly. Can you try *stateless* Keras LSTM? If you stick to...

The automatic pull may fail, and it has been added manually now. Thank you for the PR! I will close it.

My pull request (https://github.com/facebookresearch/llama/pull/202) simply made it runnable on CPU with a flag, based on the existing python script. Check it out. https://github.com/ggerganov/llama.cpp is great, despite losing the accuracy by...

[Model Maker](https://www.tensorflow.org/lite/guide/model_maker) can do transfer learning, and those models are able to run on Raspberry Pi.

Hi @ivelin , There are a couple of new tasks in progress. We will have object detection, sound classification and recommendation soon.

I can confirm that I see the similar pattern of memory leaking, and every token takes about 20M for 13B model. This happens at alpaca.cpp, while the latest version of...