diff --git a/algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/model.py b/algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/models.py
similarity index 100%
rename from algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/model.py
rename to algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/models.py
diff --git a/algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/workload.py b/algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/workload.py
index b46b125a6..43915c6dc 100644
--- a/algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/workload.py
+++ b/algorithmic_efficiency/workloads/librispeech_conformer/librispeech_pytorch/workload.py
@@ -18,7 +18,7 @@
 from algorithmic_efficiency.workloads.librispeech_conformer.input_pipeline import \
     LibriSpeechDataset
 from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch import \
-    model as conformer_model
+    models as conformer_model
 
 USE_PYTORCH_DDP, RANK, DEVICE, N_GPUS = pytorch_utils.pytorch_setup()
 
diff --git a/algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/model.py b/algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/models.py
similarity index 100%
rename from algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/model.py
rename to algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/models.py
diff --git a/algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/workload.py b/algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/workload.py
index e226e34d0..d223f328f 100644
--- a/algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/workload.py
+++ b/algorithmic_efficiency/workloads/librispeech_deepspeech/librispeech_pytorch/workload.py
@@ -6,13 +6,13 @@
 from algorithmic_efficiency import param_utils
 from algorithmic_efficiency import spec
 from algorithmic_efficiency.pytorch_utils import pytorch_setup
-from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.model import \
+from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.models import \
     initialize
 from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.workload import \
     LibriSpeechConformerWorkload
-from algorithmic_efficiency.workloads.librispeech_deepspeech.librispeech_pytorch.model import \
+from algorithmic_efficiency.workloads.librispeech_deepspeech.librispeech_pytorch.models import \
     DeepspeechConfig
-from algorithmic_efficiency.workloads.librispeech_deepspeech.librispeech_pytorch.model import \
+from algorithmic_efficiency.workloads.librispeech_deepspeech.librispeech_pytorch.models import \
     DeepspeechEncoderDecoder
 
 USE_PYTORCH_DDP, RANK, DEVICE, N_GPUS = pytorch_setup()
diff --git a/tests/test_num_params.py b/tests/test_num_params.py
index 86855d465..574fd0aa5 100644
--- a/tests/test_num_params.py
+++ b/tests/test_num_params.py
@@ -25,9 +25,9 @@
     Conformer as JaxConformer
 from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_jax.models import \
     ConformerConfig as JaxConformerConfig
-from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.model import \
+from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.models import \
     ConformerConfig as PytorchConformerConfig
-from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.model import \
+from algorithmic_efficiency.workloads.librispeech_conformer.librispeech_pytorch.models import \
     ConformerEncoderDecoder as PytorchConformer
 from algorithmic_efficiency.workloads.mnist.mnist_jax.workload import \
     _Model as JaxMLP