Adding _warmup_mmap_file function missing from MMapIndexedDataset

_warmup_mmap_file function copied over from fairseq

utils/mmap_dataset.py

@@ -43,6 +43,11 @@ def index_file_path(prefix_path):
 def data_file_path(prefix_path):
  return prefix_path + ".bin"
 
+def _warmup_mmap_file(path):
+ with open(path, "rb") as stream:
+ while stream.read(100 * 1024 * 1024):
+ pass
+
 class MMapIndexedDataset(torch.utils.data.Dataset):
  class Index(object):
  _HDR_MAGIC = b"MMIDIDX\x00\x00"
@@ -262,4 +267,4 @@ def supports_prefetch(self):
  def exists(path):
  return os.path.exists(index_file_path(path)) and os.path.exists(
  data_file_path(path)
- )
+ )