Transformers4Rec

Transformers4Rec copied to clipboard

We need to clarify in the documentation that PyT Trainer class cannot support BC and Regression. We should explain what users can use for these tasks instead of Trainer Class...

rnyak

# 🚀 Feature request Add another argument in the trainer class to check if it the task is NextItemPred, otherwise it does have to return an error msg saying that...

rnyak

[FEA] Extend HuggingFace Trainer class for multi-task learning support

1

# 🚀 Feature request ## Motivation ## Your contribution

gabrielspmoreira

[QST] Understanding the feature dependency from Example

2

# ❓ Questions & Help While training the model we are taking multiple features which also includes 'item_id-list_seq', 'category-list_seq' as categorical features and 'product_recency_days_log_norm-list_seq', 'et_dayofweek_sin-list_seq' as continuous variables. As per...

Sagar1094

[QST] How to implement a model for binary classification task?

3

# ❓ Questions & Help ## Details Thanks for making this great library! I'd like to implement a model for binary classification task with Transformers4Rec, but I encountered some errors....

brictobrick

### Description The ETL's should be updated to showcase how to generate schema.pbtxt with NVTabular.

rnyak

Is there a way for the library to handle very large sparse input, something with ? item_id: # 50 millions. session_id : 50 millions Usually, Rec are sparse data problem,...

arita37

Benchmark the new PyT data loader (with sparse tensors support) scalability with multi-GPU and larger datasets

5

Benchmark the new PyT data loader with the REES46 ecommerce dataset, using multiple GPUs Train set: All train.parquet files for 31 days (1 parquet file by week). P.s. Set row...

gabrielspmoreira

[QST] Edge compute using Transform4rec models with ONNX runtime

5

# ❓ Questions & Help ## Details I was wondering if there was a tutorial or a workflow for using Transform4rec models on edge compute using ONNX runtime? Would be...

fire

### Bug description There Is an information leakage when training TF XLNet model using `mlm` task. The returned ranking metrics are close to 1.  ### Steps/Code to reproduce bug...

sararb