Tokenization fixed

tokenization_nicheformer.py

@@ -290,6 +290,10 @@ class NicheformerTokenizer(PreTrainedTokenizer):
                     adata = ad.concat([reference_model, adata], join='outer', axis=0)
                     adata = adata[1:]
 
+            print("AFTER CONCATENATION")
+            print(f"modality dtype: {adata.obs['modality'].dtype}")
+            print(f"specie dtype: {adata.obs['specie'].dtype}") 
+            print(f"assay dtype: {adata.obs['assay'].dtype}")
             # Get gene expression data
             X = adata.X