x-transformers 1.32.10__py3-none-any.whl → 1.32.12__py3-none-any.whl

x_transformers/x_transformers.py

@@ -45,15 +45,18 @@ def default(val, d):
         return val
     return d() if callable(d) else d
 
-def cast_tuple(val, depth):
+def first(it):
+    return it[0]
+
+def is_empty(x):
+    return len(x) == 0
+
+def cast_tuple(val, depth = 1):
     return val if isinstance(val, tuple) else (val,) * depth
 
 def divisible_by(num, den):
     return (num % den) == 0
 
-def is_empty(x):
-    return len(x) == 0
-
 def maybe(fn):
     @wraps(fn)
     def inner(x, *args, **kwargs):
@@ -1922,6 +1925,7 @@ class TransformerWrapper(Module):
         attn_z_loss_weight = 1e-4,
         average_pool_embed = False,
         use_cls_token = False,
+        squeeze_out_last_dim = False
     ):
         super().__init__()
 
@@ -2006,6 +2010,10 @@ class TransformerWrapper(Module):
 
         self.memory_tokens_interspersed_every = memory_tokens_interspersed_every
 
+        # squeeze out last dimension if possible
+
+        self.squeeze_out_last_dim = squeeze_out_last_dim
+
         # whether can do cached kv decoding
 
         self.can_cache_kv = self.num_memory_tokens == 0
@@ -2173,6 +2181,14 @@ class TransformerWrapper(Module):
             else:
                 logits = self.to_logits(x)
 
+        # maybe squeeze out last dimension of logits
+
+        if self.squeeze_out_last_dim:
+            logits = tuple((rearrange(t, '... 1 -> ...') if t.shape[-1] == 1 else t) for t in cast_tuple(logits))
+
+            if not self.has_multiple_heads:
+                logits = first(logits)
+
         # different returns
 
         if return_logits_and_embeddings:

{x_transformers-1.32.10.dist-info → x_transformers-1.32.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: x-transformers
-Version: 1.32.10
+Version: 1.32.12
 Summary: X-Transformers - Pytorch
 Home-page: https://github.com/lucidrains/x-transformers
 Author: Phil Wang

{x_transformers-1.32.10.dist-info → x_transformers-1.32.12.dist-info}/RECORD

@@ -5,11 +5,11 @@ x_transformers/continuous.py,sha256=cIVEdhfei258__ziV7kQBrJMxCel54bExBTDrO9rfCI,
 x_transformers/dpo.py,sha256=LjvWgCkqTl-UuehrzQ8nkX5guLr4whYwsmm7SKSwdls,3450
 x_transformers/multi_input.py,sha256=tCh-fTJDj2ib4SMGtsa-AM8MxKzJAQSwqAXOu3HU2mg,9252
 x_transformers/nonautoregressive_wrapper.py,sha256=ys_p8obc7lTeeodCqvkRKxOXQ1C9T3j5Jwr-JbVgnXk,10432
-x_transformers/x_transformers.py,sha256=Ao3yHjEdl-qovGo9WW8q277wBHMgFxYRfcYRf1W_hKg,78076
+x_transformers/x_transformers.py,sha256=nsuYDfF4GY4kTImXEFqygnpw5mO8DOqaD_PJaeOxFS4,78549
 x_transformers/xl_autoregressive_wrapper.py,sha256=DCx4n0_c1tFai4nOqaWVnqx2p9eutsZsDMiMP1ckxNU,4117
 x_transformers/xval.py,sha256=QE1ltYZTR_eGgIHPP2BrMWVWVLqMW-OpDZh87BSmQEg,8563
-x_transformers-1.32.10.dist-info/LICENSE,sha256=As9u198X-U-vph5noInuUfqsAG2zX_oXPHDmdjwlPPY,1066
-x_transformers-1.32.10.dist-info/METADATA,sha256=DMtabf-G60PL6axX1zSsTcWcHtzvHtKQNTxHuzOFJ4A,662
-x_transformers-1.32.10.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-x_transformers-1.32.10.dist-info/top_level.txt,sha256=hO6KGpFuGucRNEtRfme4A_rGcM53AKwGP7RVlRIxS5Q,15
-x_transformers-1.32.10.dist-info/RECORD,,
+x_transformers-1.32.12.dist-info/LICENSE,sha256=As9u198X-U-vph5noInuUfqsAG2zX_oXPHDmdjwlPPY,1066
+x_transformers-1.32.12.dist-info/METADATA,sha256=oOwIIjHp8Bl1ClFKTGaiNAX3RNK46C6jmriZEbyWYvM,662
+x_transformers-1.32.12.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+x_transformers-1.32.12.dist-info/top_level.txt,sha256=hO6KGpFuGucRNEtRfme4A_rGcM53AKwGP7RVlRIxS5Q,15
+x_transformers-1.32.12.dist-info/RECORD,,