diminished block size and sparse_block_size to deal with leftovers

modeling_lsg_bert.py

@@ -59,15 +59,15 @@ class LSGBertConfig(BertConfig):
 
     def __init__(
         self,
-        adaptive=True,
         base_model_prefix="lsg",
-        block_size=128,
+        block_size=64,
+        sparse_block_size=64,
+        sparsity_factor=2,
+        adaptive=True,
         lsh_num_pre_rounds=1,
         mask_first_token=False,
         num_global_tokens=1,
         pool_with_global=True,
-        sparse_block_size=128,
-        sparsity_factor=2,
         sparsity_type="norm",
         **kwargs
         ):