coremltools 6.2 has troubles to convert the layer of mvit_block_0_transformer_0_attention

## ❓Question

Layer 55: mvit_block_0_transformer_0_LN1
Input shape: (None, 4, 1024, 144)
Output shape: (None, 4, 1024, 144)
Input spec: None
Layer 56: mvit_block_0_transformer_0_attention
Input shape: (None, 4, 1024, 144)
Output shape: (None, 4, 1024, 144)
Input spec: None

lib/python3.7/site-packages/coremltools/converters/mil/mil/operation.py", line 318, in type_value_inference
f'Core ML only supports tensors with rank <= 5. Layer "{self.name}", '
ValueError: Core ML only supports tensors with rank <= 5. Layer "reshape_16", with type "reshape", outputs a rank 6 tensor.

Any ideas?

Thanks a lot.

Start with the traceback location in coremltools/converters/mil/mil/operation.py at line 318 and the reported reshape_16 operation. Reproduce the conversion using the supplied layer shapes, then identify the model and source framework involved. Done requires a minimal reproducible case and a confirmed resolution or documented limitation.

Written by the indexing model from the issue text.