transformers/tests/models/mamba
Adibvafa Fallahpour c269c5c74d
Fix Mamba slow path bug with dtype mismatch. (#32691)
* Fix Mamba slow path bug with dtype mismatch.

* Update test_modeling_mamba.py

* Improve style.

* Fix issue with cache position of dtype mismatch test.

* Change test for slow path.

* Revert changes.

* Switch to buggy code and add test to catch it.

* Fix the dtype mismatch bug and add test code to verify it.

* Fix minor bug with test.

* Fix incorrect dtype of model output.

* Fix incorrect dtype of cache.

* Fix incorrect dtype of ssm cache.

* Fix incorrect dtype of conv state.

* Remove assertion for ssm state.

* Add assertion for conv state dtype.

* Fix all issues with dtype mismatch test.
2024-10-01 09:28:40 +02:00
..
__init__.py [Add Mamba] Adds support for the Mamba models (#28094) 2024-03-05 20:01:06 +09:00
test_modeling_mamba.py Fix Mamba slow path bug with dtype mismatch. (#32691) 2024-10-01 09:28:40 +02:00