kerighan

The layer works fine on CPU, but I have this error on tensorflow GPU: Blas xGEMV launch failed : a.shape=[1,2000000,4], b.shape=[1,4,1], m=2000000, n=1, k=4

Thanks for your package. Is there an already-implemented way of having orientation in the edges according to past/future points (edges come from future to past or the other way around)....

Update on multilingual

2

Is there any update on the multilingual tokenizers? The project seems to be on pause.

AttributeError: 'Functional' object has no attribute '_get_save_spec'

7

I get this error when trying to convert/quantize any .keras model using tflite (model was trained using TF): ``` converter = tf.lite.TFLiteConverter.from_keras_model(model) converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.target_spec.supported_types = [tf.float16] tflite_quant_model =...