diff --git a/model.py b/model.py
index 1b32cdf..71ddadb 100644
--- a/model.py
+++ b/model.py
@@ -61,7 +61,7 @@ class CausalSelfAttention(nn.Module):
         B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
 
         # calculate query, key, values for all heads in batch and move head forward to be the batch dim
-        q, k ,v  = self.c_attn(x).split(self.n_embd, dim=2)
+        q, k, v  = self.c_attn(x).split(self.n_embd, dim=2)
         k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
         q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
         v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)