Add model and requirements for sinusoidal and time embeddings

model.py

@@ -0,0 +1,42 @@
+import torch 
+import torch.nn as nn 
+import math 
+
+#Varicence scheduler 
+T = 1000
+beta_start = 1e-4
+beta_end = 0.02
+betas = torch.linspace(beta_start, beta_end, step=T)
+alphas = 1. - betas 
+alphas_cumprod = torch.cumprod(alphas, dim=0)
+
+#SinusoidalPositionEmbedding
+class Sinusoidal_embedding(torch.nn.Module):
+    def __init__(self, dim:int):
+        super().__init__()
+        assert self.dim % 2 == 0 , 'Embeddings must be divisble by 2'
+        dim = self.dim 
+
+    def forward(self, time_stamps:torch.Tensor) -> torch.Tensor :
+        half_dim = self.dim // 2
+        scale = math.log(10000)/(half_dim -1 )
+        freq = torch.exp(torch.arange(half_dim, dtype=torch.float32)* -scale)
+        embeddings = time_stamps[:, None] * freq[None, :]
+        embeddings = torch.cat((embeddings.sin(), embeddings.cos()), dim=-1)
+        return embeddings
+
+#Time Embeddings 
+class Time_embeddings(torch.nn.Module):
+    def __init__(self, in_dim:int, out_dim:int):
+        super().__init__
+        self.Sinusoidal_waves = Sinusoidal_embedding(in_dim)
+
+        self.mlp = nn.Sequential(
+            nn.Linear(in_dim, out_dim),
+            nn.SiLU(),
+            nn.Linear(out_dim , out_dim)
+        )
+
+    def forward(self, timesteps: torch.Tensor) -> torch.Tensor:
+        time_emb = self.Sinusoidal_waves(timesteps)
+        return self.mlp(time_emb)

requirements.txt

@@ -0,0 +1,3 @@
+torch
+torchvision 
+gradio