broccoli-ml 0.5.1__py3-none-any.whl → 0.5.3__py3-none-any.whl

broccoli/vit.py

@@ -91,7 +91,7 @@ class ViTEncoder(nn.Module):
         transformer_activation_kwargs: Optional[dict] = None,
         transformer_mlp_dropout=0.0,
         transformer_msa_dropout=0.1,
-        stochastic_depth=0.1,
+        transformer_stochastic_depth=0.1,
         linear_module=nn.Linear,
         initial_batch_norm=True,
     ):
@@ -285,9 +285,9 @@ class ViTEncoder(nn.Module):
                 mlp_ratio=transformer_mlp_ratio,
                 activation=transformer_activation,
                 activation_kwargs=transformer_activation_kwargs,
-                mlp_dropout=transformer_mlp_dropout,
-                msa_dropout=transformer_msa_dropout,
-                stochastic_depth=stochastic_depth,
+                transformer_mlp_dropout=transformer_mlp_dropout,
+                transformer_msa_dropout=transformer_msa_dropout,
+                stochastic_depth=transformer_stochastic_depth,
                 causal=False,
                 linear_module=linear_module,
                 bos_tokens=transformer_bos_tokens,
@@ -359,7 +359,7 @@ class CCT(nn.Module):
         transformer_activation_kwargs: Optional[dict] = None,
         transformer_mlp_dropout=0.0,
         transformer_msa_dropout=0.1,
-        stochastic_depth=0.1,
+        transformer_stochastic_depth=0.1,
         batch_norm_outputs=True,
         initial_batch_norm=True,
         linear_module=nn.Linear,
@@ -409,9 +409,9 @@ class CCT(nn.Module):
             transformer_bos_tokens=transformer_bos_tokens,
             transformer_activation=transformer_activation,
             transformer_activation_kwargs=transformer_activation_kwargs,
-            mlp_dropout=transformer_mlp_dropout,
-            msa_dropout=transformer_msa_dropout,
-            stochastic_depth=stochastic_depth,
+            transformer_mlp_dropout=transformer_mlp_dropout,
+            transformer_msa_dropout=transformer_msa_dropout,
+            transformer_stochastic_depth=transformer_stochastic_depth,
             linear_module=linear_module,
             initial_batch_norm=initial_batch_norm,
         )

{broccoli_ml-0.5.1.dist-info → broccoli_ml-0.5.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: broccoli-ml
-Version: 0.5.1
+Version: 0.5.3
 Summary: Some useful Pytorch models, circa 2025
 License: MIT
 Author: Nicholas Bailey

{broccoli_ml-0.5.1.dist-info → broccoli_ml-0.5.3.dist-info}/RECORD

@@ -10,8 +10,8 @@ broccoli/rope.py,sha256=hw7kBPNR9GQXj4GxyIAffsGKPfcTPOFh8Bc7oEHtaZY,12108
 broccoli/tensor.py,sha256=E2JK5mQwJf75e23-JGcDoT7QxQf89DJReUo2et1LhRY,1716
 broccoli/transformer.py,sha256=SwvutiYOiPlqLzbO_twye7Hna5DsJukVOzzAx9CTCyU,16417
 broccoli/utils.py,sha256=htq_hOsdhUhL0nJi9WkKiEYOjEoWqFpK5X49PtgTf-0,299
-broccoli/vit.py,sha256=CSllHj_cI0dQveuLSoHD-Y95nOqVO1F-p-8SmlJffhM,15272
-broccoli_ml-0.5.1.dist-info/LICENSE,sha256=0BAzJE5BqQ7Iixp_AFdB2W1uO-HCRX-Qfun8PHt6yVM,1073
-broccoli_ml-0.5.1.dist-info/METADATA,sha256=IFo3lnkE6Zti81jUvLuBONLlR2PUUAwj1AKqPCgFUdI,1256
-broccoli_ml-0.5.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-broccoli_ml-0.5.1.dist-info/RECORD,,
+broccoli/vit.py,sha256=DzpZPrvSJrXitKgu3TDJ4r6Pq_I4XDKjZsjbL5LUGYU,15380
+broccoli_ml-0.5.3.dist-info/LICENSE,sha256=0BAzJE5BqQ7Iixp_AFdB2W1uO-HCRX-Qfun8PHt6yVM,1073
+broccoli_ml-0.5.3.dist-info/METADATA,sha256=0WcAWopuuskj2IagQhTcEjxcuWyHXqOlAuRGEjcoGA0,1256
+broccoli_ml-0.5.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+broccoli_ml-0.5.3.dist-info/RECORD,,