worldbank REaLTabFormer issues

worldbank / REaLTabFormer

A suite of auto-regressive and Seq2Seq (sequence-to-sequence) transformer models for tabular and relational synthetic data generation.

https://worldbank.github.io/REaLTabFormer/

MIT License

193 stars 22 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Crash using model.predict() to predict a column

#81 I-Mamalikidis opened 3 days ago
0
OSError: rtf_checkpoints/not-best-disc-model does not appear to have a file named config.json,

#80 MonishSoundarRaj closed 3 weeks ago
1
Generating Balanced Synthesized Data

#79 erland-ramadhan opened 1 month ago
1
Error on mps device

#78 qzhu2017 closed 4 weeks ago
1
How can we create more synthetic data?

#77 limhasic closed 4 weeks ago
2
Use 'int64' and bump version to v0.1.7

#76 avsolatorio closed 2 months ago
0
Bug in process_datetime_data() converting datetime to int

#75 efstathios-chatzikyriakidis closed 2 months ago
2
Missing value imputation on regular data

#74 RejwankabirHamim opened 2 months ago
0
Bump version to v0.1.6

#73 avsolatorio closed 2 months ago
0
Remove use of .view when casting timestamp to int

#72 avsolatorio closed 2 months ago
0
Bug in process_datetime_data() when using pandas 2.2.1

#71 efstathios-chatzikyriakidis closed 2 months ago
1
missing data

#70 limhasic opened 3 months ago
2
RuntimeError: Error(s) in loading state_dict for GPT2LMHeadModel: size mismatch for transformer.wte.weight

#69 akefhabbal-qu opened 3 months ago
0
Documentation page not working

#68 sfragkoul closed 2 months ago
2
Question for Generate Synthetic data To compare HMA and REaLTabFormer

#67 limhasic opened 3 months ago
2
OSError: rtf_checkpoints/not-best-disc-model does not appear to have a file named config.json.

#66 AhmadKajjan-QU opened 3 months ago
2
Could order of columns affect performance of synthetic data quality?

#65 efstathios-chatzikyriakidis opened 4 months ago
2
Python datetime.date data type is handled as str and datatype handling in general

#64 efstathios-chatzikyriakidis opened 4 months ago
0
Parallelization of inference/generation in both tabular and child models.

#63 efstathios-chatzikyriakidis opened 4 months ago
0
Maximum number of columns limitation in tabular GPT-2 model?

#62 efstathios-chatzikyriakidis opened 4 months ago
0
rtf_checkpoints bug when fitting the GeoValidator example model

#61 martinjurkovic opened 5 months ago
0
Early stopping with sensitivity vs validation loss metric and the effects on synthetic data quality.

#60 efstathios-chatzikyriakidis closed 5 months ago
2
Out of memory exception on tabular model with 25k rows and 37 columns

#59 efstathios-chatzikyriakidis closed 5 months ago
3
Is it possible to run REalTabFormer on AWS Inferentia and Trainium VM instances?

#58 efstathios-chatzikyriakidis opened 5 months ago
0
Inquiries on fitting parent and child tables

#57 ThomasK1018 opened 6 months ago
0
Multi-GPU training

#56 vinay-k12 opened 6 months ago
1
Update docs requirements

#55 avsolatorio closed 8 months ago
0
Fix docs sphinx-autoapi version and run action on push to main

#54 avsolatorio closed 8 months ago
0
Apply patches and build new release

#53 avsolatorio closed 8 months ago
0
cannot import name 'is_fairscale_available' from 'transformers.integrations

#52 waylonli closed 8 months ago
1
Bug in REaLTabFormer.sample() when relational model generates no data

#51 efstathios-chatzikyriakidis closed 8 months ago
3
Bump version for release v0.1.4

#50 avsolatorio closed 8 months ago
0
Possible Improvements for CPU inference

#49 australDream opened 8 months ago
0
Conditional generation?

#48 gminorcoles closed 6 months ago
4
Possible mix-up of token columns

#47 liu305 closed 5 months ago
2
See "IndexError: index out of range in self" when related_num parameter is specified in child model sampler

#46 liu305 closed 11 months ago
1
Transaction datetime in the child table is not sequential

#45 liu305 closed 8 months ago
1
Generated datetime value in the child table is invalid

#44 liu305 opened 11 months ago
2
Running Realtab on Macs

#43 vinay-k12 closed 10 months ago
4
Logistic detection metric

#42 zechchair closed 8 months ago
5
Resolves #37: Use explicit optim="adamw_torch" to suppress deprecation warning

#41 avsolatorio closed 11 months ago
0
ERROR: multiprocess 0.70.15 has requirement dill>=0.3.7, but you'll have dill 0.3.6 which is incompatible.

#40 echatzikyriakidis opened 12 months ago
1
Add pathlib import to readme example

#39 cbusenbu closed 12 months ago
0
Docker image to run REalTabFormer to support NVIDIA CUDA and GPU

#38 echatzikyriakidis closed 12 months ago
3
Future warnings for AdamW and encoder-decoder loss (v4.12.0).

#37 echatzikyriakidis closed 11 months ago
2
Bug in model.sample() when column contains integer values while column type is string.

#36 echatzikyriakidis opened 1 year ago
1
Resolves #31: Only attempt to cast numeric values to pd.Int64Dtype type

#35 avsolatorio closed 1 year ago
0
Resolves #32: Auto-detect available device when cuda is not present

#34 avsolatorio closed 1 year ago
0
Bug when running tabular.fit() and tabular.sample() with CPU

#33 ChristinaChr opened 1 year ago
2
_validate_get_device() could be nice to be called also in model.sample() and model.predict()

#32 echatzikyriakidis closed 1 year ago
2