worldbank/REaLTabFormer

Issues

• Impute Missing Values in DataFrame Using Tabular Model

  #82 opened 5 months ago by efstathios-chatzikyriakidis
  0

• Crash using model.predict() to predict a column

  #81 opened 5 months ago by I-Mamalikidis
  0

• OSError: rtf_checkpoints/not-best-disc-model does not appear to have a file named config.json,

  #80 opened 6 months ago by MonishSoundarRaj
  1

• How can we create more synthetic data?

  #77 opened 6 months ago by limhasic
  2

• Error on mps device

  #78 opened 6 months ago by qzhu2017
  1

• Generating Balanced Synthesized Data

  #79 opened 7 months ago by erland-ramadhan
  1

• Bug in process_datetime_data() converting datetime to int

  #75 opened 8 months ago by efstathios-chatzikyriakidis
  2

• Bug in process_datetime_data() when using pandas 2.2.1

  #71 opened 8 months ago by efstathios-chatzikyriakidis
  1

• Documentation page not working

  #68 opened 8 months ago by sfragkoul
  2

• Missing value imputation on regular data

  #74 opened 8 months ago by RejwankabirHamim
  0

• Question for Generate Synthetic data To compare HMA and REaLTabFormer

  #67 opened 9 months ago by limhasic
  2

• missing data

  #70 opened 9 months ago by limhasic
  2

• RuntimeError: Error(s) in loading state_dict for GPT2LMHeadModel: size mismatch for transformer.wte.weight

  #69 opened 9 months ago by akefhabbal-qu
  0

• OSError: rtf_checkpoints/not-best-disc-model does not appear to have a file named config.json.

  #66 opened 9 months ago by AhmadKajjan-QU
  2

• Could order of columns affect performance of synthetic data quality?

  #65 opened 10 months ago by efstathios-chatzikyriakidis
  2

• Multi-GPU training

  #56 opened a year ago by vinay-k12
  1

• Python datetime.date data type is handled as str and datatype handling in general

  #64 opened 10 months ago by efstathios-chatzikyriakidis
  0

• Parallelization of inference/generation in both tabular and child models.

  #63 opened 10 months ago by efstathios-chatzikyriakidis
  0

• Maximum number of columns limitation in tabular GPT-2 model?

  #62 opened 10 months ago by efstathios-chatzikyriakidis
  0

• Early stopping with sensitivity vs validation loss metric and the effects on synthetic data quality.

  #60 opened 10 months ago by efstathios-chatzikyriakidis
  2

• Out of memory exception on tabular model with 25k rows and 37 columns

  #59 opened 10 months ago by efstathios-chatzikyriakidis
  3

• rtf_checkpoints bug when fitting the GeoValidator example model

  #61 opened 10 months ago by martinjurkovic
  0

• Possible mix-up of token columns

  #47 opened 10 months ago by liu305
  2

• Is it possible to run REalTabFormer on AWS Inferentia and Trainium VM instances?

  #58 opened a year ago by efstathios-chatzikyriakidis
  0

• Conditional generation?

  #48 opened a year ago by gminorcoles
  4

• Inquiries on fitting parent and child tables

  #57 opened a year ago by ThomasK1018
  0

• Bug in REaLTabFormer.sample() when relational model generates no data

  #51 opened a year ago by efstathios-chatzikyriakidis
  3

• cannot import name 'is_fairscale_available' from 'transformers.integrations

  #52 opened a year ago by waylonli
  1

• Logistic detection metric

  #42 opened a year ago by zechchair
  5

• Transaction datetime in the child table is not sequential

  #45 opened a year ago by liu305
  1

• Possible Improvements for CPU inference

  #49 opened a year ago by australDream
  0

• Bug in model.sample() when column contains integer values while column type is string.

  #36 opened a year ago by echatzikyriakidis
  1

• Running Realtab on Macs

  #43 opened a year ago by vinay-k12
  4

• See "IndexError: index out of range in self" when related_num parameter is specified in child model sampler

  #46 opened a year ago by liu305
  1

• Generated datetime value in the child table is invalid

  #44 opened a year ago by liu305
  2

• Future warnings for AdamW and encoder-decoder loss (v4.12.0).

  #37 opened a year ago by echatzikyriakidis
  2

• ERROR: multiprocess 0.70.15 has requirement dill>=0.3.7, but you'll have dill 0.3.6 which is incompatible.

  #40 opened a year ago by echatzikyriakidis
  1

• Docker image to run REalTabFormer to support NVIDIA CUDA and GPU

  #38 opened a year ago by echatzikyriakidis
  3

• Is it possible to do iterative training? Load the weight and retrain on new data.

  #28 opened a year ago by vinay-k12
  2

• AssertionError: The target length 10 of the data doesn't include the numeric precision at 20. Increase max_len to at least 22.

  #30 opened a year ago by vinay-k12
  2

• CPU OOM during tokenization - Tabular format

  #23 opened a year ago by mohanvrk
  3

• Bug in model.sample() when column contains integer values while column type is string.

  #31 opened a year ago by echatzikyriakidis
  5

• Bug when running tabular.fit() and tabular.sample() with CPU

  #33 opened a year ago by ChristinaChr
  2

• _validate_get_device() could be nice to be called also in model.sample() and model.predict()

  #32 opened a year ago by echatzikyriakidis
  2

• Relational Training: CUDA OOM Out of Memory Error

  #22 opened a year ago by solitaryangler
  4

• How to model a child table with multiple foreign keys?

  #29 opened a year ago by echatzikyriakidis
  0

• Speeding the training on mixed data set - categorical data, numerical and text.

  #26 opened a year ago by vinay-k12
  1

• Use different join columns (parent_join_on, child_join_on) in relational model fit method.

  #27 opened a year ago by echatzikyriakidis
  0

• Unable to complete training in colab

  #24 opened a year ago by vinay-k12
  2

• How to model N-M association tables?

  #21 opened 2 years ago by echatzikyriakidis
  0