X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=mygpt.py;h=ab4ccbc1b2168c27419e5810d07bd55d2c48665b;hb=24283925c294168184b34e9270cd7b1c7234c54a;hp=3e63567852a34449d8c280f28049d6cd70f3ecf4;hpb=b3392c295bdb75140916e2db70efc6fa50962f63;p=culture.git

diff --git a/mygpt.py b/mygpt.py
index 3e63567..ab4ccbc 100755
--- a/mygpt.py
+++ b/mygpt.py
@@ -279,13 +279,12 @@ class MyGPT(nn.Module):
         self,
         input,
         ar_mask,
+        summed_logits,
         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:
@@ -297,7 +296,7 @@ class MyGPT(nn.Module):
 
             logits = output[:, s]
 
-            logits = logits.log_softmax(dim=1) / temperature
+            logits = (logits / temperature).log_softmax(dim=-1)
 
             if forbidden_tokens is not None:
                 logits = logits.masked_fill(forbidden_tokens, float("-inf"))
@@ -306,18 +305,17 @@ class MyGPT(nn.Module):
                 logits = logits + forced_biases[None, :]
 
             if deterministic_synthesis:
-                t_next = logits.argmax(1)
+                t_next = logits.argmax(-1)
             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()
+                if summed_logits is not None:
+                    summed_logits += logits[torch.arange(t_next.size(0)), t_next].sum(
+                        dim=-1
+                    )
 
             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):