update refs to get_model_emb_dims

embs_df with all model embeddings (#363)

Add function to get number of model embeddings (#364)

clone embs_i to resolve memory leak in cls embs

update perturber stats to reflect cos sim and emb_extractor to suppress warnings for non-cls

update to account for set of perturbed genes with aggregate_data

update to enable cls emb

update tokenizer to include eos token

Update geneformer/emb_extractor.py (#350)

Upload in_silico_perturber_stats.py (#313)

fix cell state gene embeddings bug (#345)

patch datasets save_to_disk

update kwargs for pretrainer

refer to token dictionary in self

Update for gene classification (#330)

Update with gene classifier, custom token dict, and str validate options (#329)

add option for hyperparameter tuning to cc.validate

correct typo

update examples for predict_eval and handle roc for 2 cell classes

Update readthedocs for classifier

Get the gene keys and gene list keys from the token dictionary instead of medians (#304)

Prevent ruff/isort on init

Add classifier module and examples

Update geneformer/emb_extractor.py (#303)

Fix typo (#301)

Add option for variable input_size and to add CLS/SEP Tokens (#299)

add load model for train and fix validate anchor gene error

Handle case of single gene del for isp modeling of gene embs

edit docstring format to highlight options

edit docstring codeblock highlighting

update type of null_dict_list in docstring

change doc formatting

add sphinx docs

update dependencies, reinstate compatibility with python<3.9 with typing for List

Add option for modified batch size for loom tokenizer

Add functions for extracting gene embeddings, move state_embs_dict outside isp, fix bugs in isp

Add option for modifying chunk size for anndata tokenizer

tokenizer-uncropped-input_ids (#275)

fix: incorrect condition control flow (#261)

Add option to output embs as tensor

anndata_tokenizer (#170)

Fixed bugs related to overexpressing genes (#229)

Add memory-efficient method for computing emb summary statistics

Fixed bug with the double removing of indices when cell_states_to_model is false (#188)

Upload in_silico_perturber.py (#187)

Added feature to perturb a set of indices to help with debugging and with very large runtimes (#175)

Re-update stats to handle case of empty alt_states

Add handling for case of alt_states being empty list

Remove print statement from PR

Fixed bug in gen_attention_mask with len > max_len (#158)