broccoli-ml 13.0.0__py3-none-any.whl → 13.0.2__py3-none-any.whl

broccoli/transformer.py

@@ -387,13 +387,6 @@ class FeedforwardBlock(nn.Module):
         self.beta = beta
         self.xglu = activation.__name__.endswith("GLU")
 
-        if self.residual_path and (output_features < input_features):
-            raise ValueError(
-                "If the number of output features will be less than "
-                "the number of input features, then `residual_path` "
-                "should be set to False."
-            )
-
         if self.post_norm:
             self.layernorm = nn.LayerNorm(output_features)
 

broccoli/vit.py

@@ -187,9 +187,14 @@ class ViTEncoder(nn.Module):
         transformer_stochastic_depth=0.1,
         transformer_checkpoint_ff=True,
         linear_module=nn.Linear,
+        alpha=1.0,
+        beta=1.0,
     ):
         super().__init__()
 
+        self.alpha = alpha
+        self.beta = beta
+
         if cnn_activation_kwargs is not None:
             self.cnn_activation = cnn_activation(**cnn_activation_kwargs)
         else:
@@ -491,6 +496,8 @@ class ViT(nn.Module):
         batch_norm_logits=True,
         logit_projection_layer=nn.Linear,
         linear_module=nn.Linear,
+        alpha=1.0,
+        beta=1.0,
     ):
 
         super().__init__()
@@ -511,6 +518,9 @@ class ViT(nn.Module):
                 "SwiGLU": SwiGLU,
             }[transformer_activation]
 
+        self.alpha = alpha
+        self.beta = beta
+
         self.encoder = ViTEncoder(
             input_size=input_size,
             initial_batch_norm=initial_batch_norm,
@@ -559,6 +569,8 @@ class ViT(nn.Module):
             transformer_stochastic_depth=transformer_stochastic_depth,
             transformer_checkpoint_ff=transformer_checkpoint_ff,
             linear_module=linear_module,
+            alpha=alpha,
+            beta=beta,
         )
 
         self.pool = head(

{broccoli_ml-13.0.0.dist-info → broccoli_ml-13.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: broccoli-ml
-Version: 13.0.0
+Version: 13.0.2
 Summary: Some useful Pytorch models, circa 2025
 License: MIT
 Author: Nicholas Bailey

{broccoli_ml-13.0.0.dist-info → broccoli_ml-13.0.2.dist-info}/RECORD

@@ -4,10 +4,10 @@ broccoli/cnn.py,sha256=WjoPDSpe3ttwxCBNfCVRdaCHvbeZ7G-a5_i8fUsK_d8,4889
 broccoli/linear.py,sha256=W-3aNpBjd_0xRyzbCKkmg4H1qmslQOIQhB-WDDay2nM,13125
 broccoli/rope.py,sha256=GRqApBNmYCFaDak0WL1xE_BC5CTTYKQU_PBdeTcQcjc,12557
 broccoli/tensor.py,sha256=um8mrxkYbvNDo-QvHlmJm8Aw6qcngOlUZPoAk_PMReA,4480
-broccoli/transformer.py,sha256=3vAQQ75SAyr4-m3e7vSru8M-RpUy2Enp5cVUafaVYMU,28410
+broccoli/transformer.py,sha256=LoQk41Wpio2AECHLGyDxwKiR_HFoJ5l_YNpPga4Ki0I,28113
 broccoli/utils.py,sha256=oOWzn6dJ5nC_9r4zq0emmfmaYACJXJNFS48AOpW2jqc,358
-broccoli/vit.py,sha256=ZOrbfORhl29HXRDWvLt2A2WbEANJlkNdiiucFB-1CmU,22244
-broccoli_ml-13.0.0.dist-info/LICENSE,sha256=0BAzJE5BqQ7Iixp_AFdB2W1uO-HCRX-Qfun8PHt6yVM,1073
-broccoli_ml-13.0.0.dist-info/METADATA,sha256=aiwPYSEkNHgJU89jT3tYoNaF_WsaFHoRC2DhgUN7IUE,1369
-broccoli_ml-13.0.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-broccoli_ml-13.0.0.dist-info/RECORD,,
+broccoli/vit.py,sha256=jd4e6MjL2JKB8ynSQssWRh6Hs36RuLj4uWyUNVhIMUY,22472
+broccoli_ml-13.0.2.dist-info/LICENSE,sha256=0BAzJE5BqQ7Iixp_AFdB2W1uO-HCRX-Qfun8PHt6yVM,1073
+broccoli_ml-13.0.2.dist-info/METADATA,sha256=JKnTpiCVV7mo300gauy1DNHvZnv7P1-4zHIxcUTFpQ0,1369
+broccoli_ml-13.0.2.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+broccoli_ml-13.0.2.dist-info/RECORD,,