54a2361a29
* Adding _tie_weights() to prediction heads to support low_cpu_mem_usage=True * Testing for the non-safe-tensors case, since the default is safe-tensors already * Running fixup/fix-copies * Adding accelerate annotations to tests |
||
---|---|---|
.. | ||
__init__.py | ||
test_modeling_musicgen.py | ||
test_processing_musicgen.py |