I always notice this too. Getting it right seems (psychologically for me anyway) to be a big part of "a good pelican" whenever I look at these. But doesn't always seem to correlate with increasing intelligence of models (measured via benchmarks, experience with the model etc.).

It's not frontier pelican without the back leg behind the bike frame IMO.

Nice, captured the flavour of 5's writing exactly.

Approx ~131 million total. Made up of estimated:

102M - modified BERT-base-Chinese text encoder

26M - 3D U-Net-style vision/anatomy encoder

2.8M - projection layers, anatomy-specific projections, query tokens and attention layer

Written to run on something like an H100 though- as the CT Scan data is quite large.