*   `tf.math.argmin`/`tf.math.argmax` for input data type `tf.bool` on
            CPU.
        *   `tf.nn.gelu` op for output data type `tf.float32` and quantization
            on CPU.
    *   Add nominal support for unsigned 16-bit integer tensor types. Note that
        very few TFLite kernels support this type natively, so its use in mobile
        ML authoring is generally discouraged.

2066..2069    ; disallowed                             # 6.3  LEFT-TO-RIGHT ISOLATE..POP DIRECTIONAL ISOLATE
206A..206F    ; disallowed                             # 1.1  INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES
2070          ; mapped                 ; 0030          # 1.1  SUPERSCRIPT ZERO
2071          ; mapped                 ; 0069          # 3.2  SUPERSCRIPT LATIN SMALL LETTER I