Update README.md

README.md

@@ -5,11 +5,11 @@ license: mit
 
 A semi custom network trained from scratch for 799 epochs based on the follow paper [Simpler Diffusion (SiD2)](https://arxiv.org/abs/2410.19324v1)
 
-[Modeling](https://huggingface.co/Blackroot/SimpleDiffusion-TensorProductAttentionRope/blob/main/models/uvit.py) || [Training](https://huggingface.co/Blackroot/SimpleDiffusion-TensorProductAttentionRope/blob/main/train.py)
+[Modeling](./blob/main/models/uvit.py) || [Training](./blob/main/train.py)
 
 This network uses the optimal transport flow matching objective outlined [Flow Matching for Generative Modeling](https://arxiv.org/abs/2210.02747)
 
-A modified tensor product attention with rope is used instead of regular MHA [Tensor Product Attention is All You Need](https://arxiv.org/abs/2501.06425)
+This is using multi head attention with no positional embeddings. [The Impact of Positional Encoding on Length Generalization in Transformers](https://arxiv.org/abs/2305.19466)
 
 xATGLU Layers are used in some places [Expanded Gating Ranges Improve Activation Functions](https://arxiv.org/pdf/2405.20768)