Exclude strings from v3.2+ source vector checks (explosion#9697)

Exclude strings from `Vector.to_bytes()` comparions for v3.2+ `Vectors`
that now include the string store so that the source vector comparison
is only comparing the vectors and not the strings.

spacy/language.py

@@ -701,7 +701,8 @@ def create_pipe_from_source(
  if (
  self.vocab.vectors.shape != source.vocab.vectors.shape
  or self.vocab.vectors.key2row != source.vocab.vectors.key2row
- or self.vocab.vectors.to_bytes() != source.vocab.vectors.to_bytes()
+ or self.vocab.vectors.to_bytes(exclude=["strings"])
+ != source.vocab.vectors.to_bytes(exclude=["strings"])
  ):
  warnings.warn(Warnings.W113.format(name=source_name))
  if source_name not in source.component_names:
@@ -1822,7 +1823,9 @@ def from_config(
  )
  if model not in source_nlp_vectors_hashes:
  source_nlp_vectors_hashes[model] = hash(
- source_nlps[model].vocab.vectors.to_bytes()
+ source_nlps[model].vocab.vectors.to_bytes(
+ exclude=["strings"]
+ )
  )
  if "_sourced_vectors_hashes" not in nlp.meta:
  nlp.meta["_sourced_vectors_hashes"] = {}

spacy/training/initialize.py

@@ -132,7 +132,7 @@ def init_vocab(
  logger.info(f"Added vectors: {vectors}")
  # warn if source model vectors are not identical
  sourced_vectors_hashes = nlp.meta.pop("_sourced_vectors_hashes", {})
- vectors_hash = hash(nlp.vocab.vectors.to_bytes())
+ vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"]))
  for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items():
  if vectors_hash != sourced_vectors_hash:
  warnings.warn(Warnings.W113.format(name=sourced_component))