Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,11 @@ license: mit
|
|
5 |
|
6 |
A semi custom network based on the follow paper [Simpler Diffusion (SiD2)](https://arxiv.org/abs/2410.19324v1)
|
7 |
|
|
|
|
|
|
|
|
|
|
|
8 |

|
9 |

|
10 |

|
|
|
5 |
|
6 |
A semi custom network based on the follow paper [Simpler Diffusion (SiD2)](https://arxiv.org/abs/2410.19324v1)
|
7 |
|
8 |
+
This network uses the optimal transport flow matching objective outlined [Flow Matching for Generative Modeling](https://arxiv.org/abs/2210.02747)
|
9 |
+
|
10 |
+
xATGLU Layers are used instead of linears for entry into the transformer MLP layer [Expanded Gating Ranges
|
11 |
+
Improve Activation Functions](https://arxiv.org/pdf/2405.20768)
|
12 |
+
|
13 |

|
14 |

|
15 |

|