Hannes Hapke

Hi @shuklak13, Thank you for sharing the detailed design doc. I left a few comments in the design doc. Happy to chat more about it if you like. Sync or...

Specifying `custom_objects` when loading a saved similarity model fails at the moment. The only way to load a similarity model saved from TensorFlow Similarity is only possible as follows: ```...

Wow, what a timing @rcrowe-google. We just discussed this topic in the MCT meeting this morning as part of the framework agnostic MCT. @sayakpaul @deep-diver @merveenoyan If you can, please...

@merveenoyan Thank you for offering your help! We are currently collecting the different model/attributes the MCT should support. @deutranium is working on a comparison. If you can, join our next...

Hi @merveenoyan, From your experience with the HuggingFace model cards, do you see anything missing in the original MCT proto (https://github.com/tensorflow/model-card-toolkit/blob/main/model_card_toolkit/proto/model_card.proto)? We would love to add it in the future...

Hi @broken, Do you know what the status of the `tf.text` for tf.lite is? Converting a model with tf.text works, but invoking it fails (TF 2.9) with ``` RuntimeError: Table...

Just found this amazing resource: https://www.tensorflow.org/text/guide/text_tf_lite It solved the `RuntimeError`. Only certain tokenizers can be converted to `TFlite`. The link above contains the list of convertable `TFtext` classes.

@broken Thank you for the detailed reply and explanations. I have tried to convert a model with the `FastBertTokenizer` to `uint8`, but the converted failed because the `FastBertTokenizer` op isn't...

Thank you @codesue for linking the `yapf` issue. The issue is open for 3+ years and the consensus is > use black to change the quote and then use yapf...

@deep-diver Great component idea. How will you handle the different prompts for optimal performance? Do you have code you could share?