Ian Tenney

This looks like a fairly low-level error. Are you able to run any of the examples from https://github.com/huggingface/transformers? This one uses TF2 and the same underlying Keras models as our...

This does look like a much lower-level error than LIT, unfortunately. Some issues on the TensorFlow tracker point to GPU memory: https://github.com/tensorflow/tensorflow/issues/25403 and specific issues with RTX cards needing a...

By global/model, do you mean things like metrics? The interpreter API is very general and we use it for both; in the case of something like a salience map (such...

Yes! It's on our roadmap to support something like this. We don't have it in the UI yet, but in the mean time you can use the salience components offline...

Can you print the contents of `batched_outputs`, including types? The error above: ``` TypeError: (-0.7481077572209469+0j) is not JSON serializable. ``` Looks like the value is a complex number `a+bj`, which...

Thanks, all of those values look okay although the indentation is very strange so I could be missing something. Can you post the error you're still seeing? You might try...

It's on the roadmap to have more "seamless" integration with more frameworks, including TensorFlow Serving, but no ETA yet. That being said: for a specific model, if you have a...

@kumarvrsec did the above (building the client) resolve this? Yarn needs to run to compile the typescript and produce the main.js file; we've set it to also copy the other...

That's odd - possible that you're running from an environment that can't access the hosted files for HuggingFace Transformers? If so, you can manually download from https://huggingface.co/bert-base-uncased#list-files and pass a...

Did you run `yarn && yarn build`?