nvidia
/

Llama-3_1-Nemotron-51B-Instruct

Text Generation

Model card Files Files and versions Community

itlevy commited on 3 days ago

Commit

66b02b3

•

1 Parent(s): b5dfaf4

v4.45 support

Files changed (1) hide show

variable_cache.py +1 -0

variable_cache.py CHANGED Viewed

@@ -38,6 +38,7 @@ class VariableCache(Cache_4_44_2, Cache):
                  max_cache_len: int | None,
                  device: torch.device | str | None = None,
                  dtype: torch.dtype | None = None,
                  ):
         Cache_4_44_2.__init__(self)

                  max_cache_len: int | None,
                  device: torch.device | str | None = None,
                  dtype: torch.dtype | None = None,
+                 **kwargs: Any,
                  ):
         Cache_4_44_2.__init__(self)