rxnn 0.2.27__py3-none-any.whl → 0.2.29__py3-none-any.whl

rxnn/training/models.py

@@ -128,7 +128,7 @@ class MrlActorModel(nn.Module):
         return list(set(
             self.encoder.memory_parameters() +
             self.decoder.memory_parameters() +
-            self.memory_attention.parameters()
+            list(self.memory_attention.parameters())
         ))
 
     def memory_cross_attention_parameters(self) -> list[nn.Parameter]:
@@ -140,7 +140,6 @@ class MrlActorModel(nn.Module):
     def memory_attention_parameters(self) -> Iterator[nn.Parameter]:
         return self.memory_attention.parameters()
 
-
     def not_memory_parameters(self) -> list[nn.Parameter]:
         return list(set(
             self.encoder.not_memory_parameters() +

rxnn/transformers/layers.py

@@ -68,8 +68,8 @@ class ReactiveTransformerLayer(nn.Module):
         return list(self.memory_cross_attention.parameters()) + list(self.norm2.parameters())
 
     def not_memory_parameters(self) -> list[nn.Parameter]:
-        memory_params = self.memory_parameters()
-        return [param for param in self.parameters() if param not in memory_params]
+        return (list(self.attention.parameters()) + list(self.norm1.parameters()) +
+                list(self.norm3.parameters()) + list(self.ff.parameters()))
 
     def update_max_len(self, max_seq_len: int):
         if self.attention.rope is not None:

{rxnn-0.2.27.dist-info → rxnn-0.2.29.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rxnn
-Version: 0.2.27
+Version: 0.2.29
 Summary: RxNN: Reactive Neural Networks Platform
 License: Apache-2.0
 Keywords: deep-learning,ai,machine-learning

{rxnn-0.2.27.dist-info → rxnn-0.2.29.dist-info}/RECORD

@@ -15,7 +15,7 @@ rxnn/training/base.py,sha256=_xik1GXE4RJ_nxwqLQ1ccXA5pRtBCi-jL-jeRFBdHBU,11851
 rxnn/training/bml.py,sha256=FJszaQXOLx2ZHBa1CQpyMrG8i4Kj14E-gzDAEK_Ei5k,17272
 rxnn/training/callbacks.py,sha256=-N0MQPpZQaUWCINdTOsjul4bDGbGr2JgQBqOIXBLS6o,35053
 rxnn/training/dataset.py,sha256=7hTilFWPpqUEc6zNcMqBPjxFKxCfvTKKF3E8tVlwccQ,51250
-rxnn/training/models.py,sha256=bY6yZoXYJEsrcymtb5Ep41vmFVHplCGWlrw1dI0oFRc,6807
+rxnn/training/models.py,sha256=2KhNT7yx0AgUke4nmsFqzQKx_YYp78QvsLWYZjWeUgQ,6812
 rxnn/training/mrl.py,sha256=MnLaYWxblc5cF261R5PNjIvddVQVNxyjAkEYtchBn9E,49299
 rxnn/training/reward.py,sha256=7MTVdNm5HnWmt6zFDi3TAYmnVSL_-24riOoY2F7z4x8,11290
 rxnn/training/rl.py,sha256=j-KNLoZjhaEKasYNOc8DxHtwvknAgAJFwvXKot6otFA,3272
@@ -25,14 +25,14 @@ rxnn/training/utils.py,sha256=Bw8nZLKIt7NQpUVCYkb_79kWKChVFOYgYXwODo4SvNc,5718
 rxnn/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rxnn/transformers/attention.py,sha256=d0Igo1Nrn76BphbHrzekiKJfT3RCy4iSXSB6FLAOTgc,16247
 rxnn/transformers/ff.py,sha256=jJnuBDsnnX5uYC_WZH8cXAYrMnz0P-iX7MwcPivjRtI,2533
-rxnn/transformers/layers.py,sha256=LXSY829fIHSCmFmClhQ6B7I5aKbiOqy9mZmwlJG_r7U,7961
+rxnn/transformers/layers.py,sha256=l0bXmhN7KOkCw0KTVLixWSo9Op4SesGabWJ4R4EQBMY,7988
 rxnn/transformers/mask.py,sha256=J0cfLVLt3SzS2ra3KcY4khrkhI975Dw4CjpUi3Sn25s,419
 rxnn/transformers/models.py,sha256=QwVxYN9DrKllEpOiFoAx4CiThOWafeTa-OAY7L6gN0Y,8929
 rxnn/transformers/moe.py,sha256=j6jEx6Ip0zttlUZKKn82azxo95lkLZs-H2GLSMD88hY,5859
 rxnn/transformers/positional.py,sha256=1PjcJybUzeQlIKJI4tahAGZcYgCRCL0otxs7mpsNuzM,4410
 rxnn/transformers/sampler.py,sha256=t6iiQTdLQ0TakUWnnhKkb5DKF2F_9-thXHBydDF3fxg,17389
 rxnn/utils.py,sha256=ihb6OTyDtPiocB_lOvnq7eOkjjpCkgs8wxvXUBNQ7mM,996
-rxnn-0.2.27.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
-rxnn-0.2.27.dist-info/METADATA,sha256=woZT3PVGgtEJP7DIAJv1-Mdfd4XvKoCRHANQgoTXoXk,25960
-rxnn-0.2.27.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-rxnn-0.2.27.dist-info/RECORD,,
+rxnn-0.2.29.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
+rxnn-0.2.29.dist-info/METADATA,sha256=WVEyKmyYbMOb5sm7vjjnCN9j8ABz0QfGJCYkQbWvwT8,25960
+rxnn-0.2.29.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+rxnn-0.2.29.dist-info/RECORD,,