Hugging Face's logo

ctheodoris
/
Geneformer

Fill-Mask
Transformers
Safetensors
bert
single-cell
genomics
Model card Files
xet
 Community
597
Geneformer

Commit History

  1. Raise error for train and validation mismatch

    madhavanvenkatesh
    Verified signature
    83f83fd

  2. Upload in_silico_perturber.py (#432)⁠

    ctheodoris +1: davidjwen
    Verified signature
    cb89107

  1. Update geneformer/emb_extractor.py (#453)⁠

    ctheodoris +1: hchen725
    Verified signature
    ebc1e09

  2. Update geneformer/tokenizer.py (#450)⁠

    ctheodoris +1: hchen725
    Verified signature
    664f71e

  1. update isp default mode to cls

    ctheodoris
    Verified signature
    0c99403

  1. Adding tags to the model (#448)⁠

    ctheodoris +1: canergen
    Verified signature
    3a68669

  1. update transformers version to match pretrainer using accelerate

    ctheodoris
    Verified signature
    3d62bb9

  2. update pretrainer to not use distributed sampler (Trainer uses accelerate)

    ctheodoris
    Verified signature
    8140c51

  1. update function for N_Detections for mixture_model without anchor_token

    Christina Theodoris
    df297bc

  1. add check to ensure emb_label is None for getting state embs dict

    Christina Theodoris
    39b4444

  1. change default emb to cls

    ctheodoris
    Verified signature
    9ee140a

  1. include install time in model card

    ctheodoris
    Verified signature
    21d36cd

  1. Update trainer output dir (#427)⁠

    ctheodoris +1: hchen725
    Verified signature
    dc23c5f

  1. Update geneformer/tokenizer.py (#415)⁠

    ctheodoris +1: hchen725
    Verified signature
    63275a8

  2. Create multi-task_cell_classification.ipynb (#418)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    b138ba5

  1. CUDA kernels incompatible with standard PyTorch device movement with 4bit/8bit, necessitating device-specific handling (#416)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    b6d28c3

  1. Add find_packages to automatically include mtl and subpackages in setup.py (#410)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    3b78204

  2. adding tensorboard to setup.py (#409)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    94d98d1

  3. tensorboard add to reqs (#407)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    e8fa43a

  1. dictionaries from parent dir (#405)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    85f295e

  2. remove token dictionary and unpickling from init (#403)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    7eca269

  1. move dict loading to function in eval utils

    ctheodoris
    57bc17e

  2. edit doc formatting

    ctheodoris
    fce3f6e

  3. edit docs formatting

    ctheodoris
    ef094b2

  4. add mtl_classifier to docs

    ctheodoris
    bedb3b7

  5. add input size tip to instructions

    ctheodoris
    Verified signature
    2732369

  6. update tokenizer to defaults for 95M models for special token and input size

    ctheodoris
    Verified signature
    da8cf3d

  7. update instructions to include reminder about token dictionary

    ctheodoris
    Verified signature
    cb1b0d5

  1. pointing dictionaries from the mtl module's init (#397)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    7470753

  2. Refactored token dictionary loading and encapsulated dictionary (#398)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    beb62a4

  3. Refactor: Convert mask_token_id, pad_token_id, and all_special_ids to properties (#395)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    2e06f1a

  1. sync token_dictionary variable name w/ classifier

    ctheodoris
    Verified signature
    a021deb

  1. update setup with req and manifest with updated filenames

    ctheodoris
    a34fbc2

  1. fix imports mtl/eval_utils

    ctheodoris
    eab1878

  1. allow model_type valid options to take params model_type : {"Pretrained", "GeneClassifier", "CellClassifier", "MTLCellClassifier", "MTLCellClassifier-Quantized"} (#390)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    47e0ef8

  2. peft>=0.11.1 (#387)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    4c9dda5

  3. "save_model_without_heads" is redundant (#385)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    de10ab0

  4. comment out "def save_model_without_heads(original_model_save_directory)"; redundant for ISP/Emb extractor (#382)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    22bf20f

  5. fixed bug related to dynamic ranges in dictionary with 'min' and 'max' value mismatch in optuna suggest fn (#380)⁠

    ctheodoris +1: madhavanvenkatesh
    Verified signature
    fe1640b

  1. Update README.md

    ctheodoris
    Verified signature
    11bcee7

  1. precommit formatting

    ctheodoris
    f07bfd7

  2. update with 12L and 20L i4096 gc95M models, multitask and quantiz code

    ctheodoris
    933ca80

  1. rename for consistency

    ctheodoris
    Verified signature
    ec19834

  2. delete old gene name dict

    ctheodoris
    Verified signature
    817eca2

  3. update to only have gene names as keys in gene_name_id_dict

    ctheodoris
    Verified signature
    e61485e

  4. Add function for summing of Ensembl IDs (#377)⁠

    ctheodoris +1: hchen725
    Verified signature
    1e18102

  1. save pval

    ctheodoris
    b07f4b1

  2. add typing list import

    ctheodoris
    42053dc

  1. move dicts to init

    ctheodoris
    ea428cb

  2. add random state to umap

    ctheodoris
    eb2a04b