ensure anndata/zarr returns data rather than dir if not collapse_gene_ids

geneformer/tokenizer.py

@@ -240,7 +240,7 @@ def sum_ensembl_ids(
                 gene for gene in ensembl_ids if gene in gene_token_dict.keys()
             ]
             if len(ensembl_id_check) == len(set(ensembl_id_check)):
-                return data_directory
+                return data
             else:
                 raise ValueError("Error: data Ensembl IDs non-unique.")