x-transformers 1.40.1__py3-none-any.whl → 1.40.3__py3-none-any.whl

x_transformers/x_transformers.py

@@ -442,10 +442,10 @@ class DynamicPositionBias(Module):
         return bias
 
 class AlibiPositionalBias(Module):
-    def __init__(self, heads, total_heads, **kwargs):
+    def __init__(self, heads, total_heads = None, **kwargs):
         super().__init__()
         self.heads = heads
-        self.total_heads = total_heads
+        self.total_heads = default(total_heads, heads)
 
         slopes = Tensor(self._get_slopes(heads))
         slopes = rearrange(slopes, 'h -> h 1 1')
@@ -1107,6 +1107,7 @@ class Attention(Module):
         context_mask = None,
         attn_mask = None,
         rel_pos = None,
+        attn_bias = None,
         rotary_pos_emb = None,
         prev_attn = None,
         mem = None,
@@ -1237,8 +1238,8 @@ class Attention(Module):
 
         # prepare relative positional bias, if needed
 
-        attn_bias = None
         if exists(rel_pos):
+            assert not exists(attn_bias)
             attn_bias = rel_pos(i, j)
             attn_bias = pad_at_dim(attn_bias, (num_mem_kv, 0), value = 0.) # handle memory key / values
 
@@ -1664,6 +1665,7 @@ class AttentionLayers(Module):
         cache_age = 1,
         return_hiddens = False,
         rotary_pos_emb = None,
+        attn_bias = None,
         condition = None,
         layers_execute_order: tuple[int, ...] | None = None
     ):
@@ -1817,7 +1819,7 @@ class AttentionLayers(Module):
             block = partial(block, **block_forward_kwargs)
 
             if layer_type == 'a':
-                out, inter = block(x, mask = mask, context_mask = self_attn_kv_mask, attn_mask = attn_mask, rel_pos = self.rel_pos, rotary_pos_emb = rotary_pos_emb, prev_attn = prev_attn, cache = next(iter_attn_cache, None), mem = layer_mem, mem_mask = layer_mem_mask, return_intermediates = True)
+                out, inter = block(x, mask = mask, context_mask = self_attn_kv_mask, attn_mask = attn_mask, rel_pos = self.rel_pos, rotary_pos_emb = rotary_pos_emb, prev_attn = prev_attn, cache = next(iter_attn_cache, None), mem = layer_mem, mem_mask = layer_mem_mask, attn_bias = attn_bias, return_intermediates = True)
             elif layer_type == 'c':
                 out, inter = block(x, context = context, mask = mask, context_mask = context_mask, prev_attn = prev_cross_attn, cache = next(iter_attn_cache, None), return_intermediates = True)
             elif layer_type == 'f':

{x_transformers-1.40.1.dist-info → x_transformers-1.40.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: x-transformers
-Version: 1.40.1
+Version: 1.40.3
 Summary: X-Transformers - Pytorch
 Home-page: https://github.com/lucidrains/x-transformers
 Author: Phil Wang

{x_transformers-1.40.1.dist-info → x_transformers-1.40.3.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=2NU58hYMgn-4Jzg3mie-mXb0XH_dCN7fjlzd3K1rLUY,10510
-x_transformers/x_transformers.py,sha256=TGXJZXCWR5BiMkS5Kx-JhFQ85AxkiJabLiHnrCTC874,84562
+x_transformers/x_transformers.py,sha256=17wNbMh5Mt6cyrAvkBToIozmFt-p9ZBhQCqqlnDyHPI,84676
 x_transformers/xl_autoregressive_wrapper.py,sha256=CvZMJ6A6PA-Y_bQAhnORwjJBSl6Vjq2IdW5KTdk8NI8,4195
 x_transformers/xval.py,sha256=QE1ltYZTR_eGgIHPP2BrMWVWVLqMW-OpDZh87BSmQEg,8563
-x_transformers-1.40.1.dist-info/LICENSE,sha256=As9u198X-U-vph5noInuUfqsAG2zX_oXPHDmdjwlPPY,1066
-x_transformers-1.40.1.dist-info/METADATA,sha256=WouMl3Ld1llknOwj7BcKi-_YZ9Hx9RZ-ni-eGCP_uQY,661
-x_transformers-1.40.1.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-x_transformers-1.40.1.dist-info/top_level.txt,sha256=hO6KGpFuGucRNEtRfme4A_rGcM53AKwGP7RVlRIxS5Q,15
-x_transformers-1.40.1.dist-info/RECORD,,
+x_transformers-1.40.3.dist-info/LICENSE,sha256=As9u198X-U-vph5noInuUfqsAG2zX_oXPHDmdjwlPPY,1066
+x_transformers-1.40.3.dist-info/METADATA,sha256=2Qb9WF8pa8bmqMI4VdO9f9bBEmKMcUatlbcU2SDJGwM,661
+x_transformers-1.40.3.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+x_transformers-1.40.3.dist-info/top_level.txt,sha256=hO6KGpFuGucRNEtRfme4A_rGcM53AKwGP7RVlRIxS5Q,15
+x_transformers-1.40.3.dist-info/RECORD,,