fix exact_mean subselection to be for index rather than col name a13a2cf Christina Theodoris commited on 3 days ago
fix exact_mean and exact_median to subselect dataframe emb cols, not cell rows cfc8cdb Christina Theodoris commited on 4 days ago
Prepare data cell level pass cell state dict instead of genes (#483) 69e6887 verified ctheodoris hchen725 commited on Feb 5
ensure gene class dict only inverted when using gene classifier 54b408b Christina Theodoris commited on Feb 5
Fix how mappings and train and val data are returned (#473) c81f6f9 verified ctheodoris hchen725 commited on Jan 27
Add checks for custom attributes and n_counts prior to sum ensembl id (#461) 09de197 verified ctheodoris hchen725 commited on Dec 4, 2024
further emphasize different token dictionaries in examples e2ee685 Christina Theodoris commited on Dec 4, 2024
remove unused imports while no longer using distributed sampler b9028ba verified ctheodoris commited on Dec 4, 2024
Raise error for train and validation mismatch (#459) 9af94b8 verified ctheodoris madhavanvenkatesh commited on Dec 4, 2024
Update geneformer/emb_extractor.py (#453) ebc1e09 verified ctheodoris hchen725 commited on Nov 22, 2024
update transformers version to match pretrainer using accelerate 3d62bb9 verified ctheodoris commited on Nov 7, 2024
update pretrainer to not use distributed sampler (Trainer uses accelerate) 8140c51 verified ctheodoris commited on Nov 7, 2024
update function for N_Detections for mixture_model without anchor_token df297bc Christina Theodoris commited on Oct 25, 2024
add check to ensure emb_label is None for getting state embs dict 39b4444 Christina Theodoris commited on Oct 23, 2024
Create multi-task_cell_classification.ipynb (#418) b138ba5 verified ctheodoris madhavanvenkatesh commited on Sep 13, 2024
CUDA kernels incompatible with standard PyTorch device movement with 4bit/8bit, necessitating device-specific handling (#416) b6d28c3 verified ctheodoris madhavanvenkatesh commited on Sep 10, 2024
Add find_packages to automatically include mtl and subpackages in setup.py (#410) 3b78204 verified ctheodoris madhavanvenkatesh commited on Sep 5, 2024
adding tensorboard to setup.py (#409) 94d98d1 verified ctheodoris madhavanvenkatesh commited on Sep 5, 2024
dictionaries from parent dir (#405) 85f295e verified ctheodoris madhavanvenkatesh commited on Sep 3, 2024
remove token dictionary and unpickling from init (#403) 7eca269 verified ctheodoris madhavanvenkatesh commited on Sep 3, 2024
update tokenizer to defaults for 95M models for special token and input size da8cf3d verified ctheodoris commited on Sep 2, 2024
update instructions to include reminder about token dictionary cb1b0d5 verified ctheodoris commited on Sep 2, 2024
pointing dictionaries from the mtl module's init (#397) 7470753 verified ctheodoris madhavanvenkatesh commited on Aug 28, 2024
Refactored token dictionary loading and encapsulated dictionary (#398) beb62a4 verified ctheodoris madhavanvenkatesh commited on Aug 28, 2024
Refactor: Convert mask_token_id, pad_token_id, and all_special_ids to properties (#395) 2e06f1a verified ctheodoris madhavanvenkatesh commited on Aug 28, 2024
sync token_dictionary variable name w/ classifier a021deb verified ctheodoris commited on Aug 26, 2024
update setup with req and manifest with updated filenames a34fbc2 ctheodoris commited on Aug 21, 2024
allow model_type valid options to take params model_type : {"Pretrained", "GeneClassifier", "CellClassifier", "MTLCellClassifier", "MTLCellClassifier-Quantized"} (#390) 47e0ef8 verified ctheodoris madhavanvenkatesh commited on Aug 21, 2024
"save_model_without_heads" is redundant (#385) de10ab0 verified ctheodoris madhavanvenkatesh commited on Aug 21, 2024