Update.

[culture.git] / mygpt.py

diff --git a/mygpt.py b/mygpt.py
index 131c822..7117e76 100755 (executable)
--- a/mygpt.py
+++ b/mygpt.py
@@ -279,10 +279,12 @@ class MyGPT(nn.Module):
         self,
         input,
         ar_mask,
+        temperature=1.0,
         deterministic_synthesis=False,
         forbidden_tokens=None,
         forced_biases=None,
     ):
+        sum_logits = 0
         to_generate = (ar_mask.sum(0) > 0).nonzero()
         if to_generate.min() > 0:
             self(
@@ -300,8 +302,13 @@ class MyGPT(nn.Module):
             else:
                 dist = torch.distributions.categorical.Categorical(logits=logits)
                 t_next = dist.sample()
+                sum_logits += logits.log_softmax(dim=-1)[
+                    torch.arange(t_next.size(0)), t_next
+                ].sum()
             input[:, s] = ar_mask[:, s] * t_next + (1 - ar_mask[:, s]) * input[:, s]
 
+        return sum_logits
+
     def record_attention(self, v=True):
         for m in self.modules():
             if isinstance(m, QKVAttention):