Addressed issues for tokenizer, anndata tokenizer now uses a fraction of memory

Generalized

Added anndata tokenizer and switched to Dataset.from_generator

Add error for no files found and suppress loompy import warning

Update tokenizer to allow tokenization without custom cell attributes

Modify tokenizer to allow renaming attr names btwn loom and .dataset

Add further explanation regarding input file format for transcriptome tokenizer

Add further explanation to tokenizer example script and updated tokenizer to match loompy raised error

Fix bug with metadata when processing multiple .loom files (#3)

Add data collator for cell classification and example for cell classification

Add Geneformer tokenizer and updated model card