Update minor formatting

Config head node runtime via IP

Fixed error with perturbing individual genes and updated ways to specify cell_states_to_model (#146)

Rename heatmap legend to be correct label

Add function to extract and plot cell embeddings

Update isp to allow modeling single perturbation in multiple cells as batches

Change list of individual IDs to set to ensure unique before subsetting into train/valid/test sets

Add note to recommend tuning hyperparameters for downstream applications

Add instructions to convert gene annotations w/ Ensembl Biomart

Remove unused evalset variable from cell classification example

Update links including unsorted example lengths file

Add uniform max len for padding for predictions

Add example code for obtaining non-zero median digests

Add further explanation regarding input file format for transcriptome tokenizer

Update instructions in tokenizing example to clarify requirement for Ensembl ID

Update instructions in tokenizing example to clarify requirement for Ensembl ID

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

Move example input files to dataset repository to include example datasets for fine-tuning

Add example for tokenizing .loom dataset

Update gene classification example to create directory after training arguments are defined

Subclass collator for cell classification

Update pretrainer for transformers==4.28.0

Add example input labels for distinguishing bivalent promoters.

Add in silico perturbation example notebook.

Add example input files for gene classification of TF dosage sensitivity

Add example for hyperparameter optimization for disease classifier

Add data collator for gene classification and example for gene classification

Add data collator for cell classification and example for cell classification

Add Geneformer trainer and pretraining example