Transformers4Rec

Transformers4Rec copied to clipboard

Update getting started ETL notebook to generate schema file from nvt and training nb to read the schema file

3

rnyak

[QST] Understanding Model Predictions and visualize_response Function

6

# ❓ Questions & Help ## Details Hi all, I am trying to understand the model output and how its converted into `top_k` items using the function provided [here](https://github.com/NVIDIA-Merlin/Transformers4Rec/blob/main/transformers4rec/torch/utils/examples_utils.py) ```...

SaadAhmed433

[BUG] Mismatch between total number of items and length of prediction logit values (end-to-end-session-based notebook)

6

### Bug description In the example [here](https://github.com/NVIDIA-Merlin/Transformers4Rec/tree/main/examples/end-to-end-session-based) (using the Tensorflow approach), after we perform ETL with NVTabular, train the model with Tensorflow, and deploy it into Triton Server, there is...

hosseinkalbasi

# 🚀 Feature request There is an open [issue](https://github.com/NVIDIA-Merlin/Transformers4Rec/issues/28 ) reporting that the NVT PyT data-loader is not correctly supporting `torch.nn.parallel.DistributedDataParallel`. This feature is to expose the missing option in...

sararb

[BUG] Single k in top_ks metric leads to an error caused by iteration over 0-d tensor

4

### Bug description Using a single k as `top_ks` parameter to a metric like e.g. `RecallAt(top_ks=[4])` leads to a `TypeError: iteration over a 0-d tensor` when `zip(metric, topks[name])` is run...

juriwiens

[QST] - Multi-GPU Support w/ Naive model.fit()

13

# ❓ Questions & Help ## Details Hello! My team is using T4Rec w/ a BinaryClassificationTask Head. We are utilizing the recommended class method `model.fit()` rather than the trainer class....

jacobdineen

[QST] Training time for different models and datasets

1

# ❓ Questions & Help I'm looking for people's experience in training different LM architectures from scratch on different datasets. ## Details What dataset + Language model did you use?...

SalvadorMartiRoman

[QST] Recommend items for a user based on the sequence of her prior baskets

1

# ❓ Questions & Help ## Details In the current examples, Transformers4Rec takes the sequential interactions in a session to predict the next item. Can we use this framework for...

shihuidai

[QST] How to pad a list of lists column?

1

Thank you for the amazing work! I have a following use case: 1. After applying the groupby operation of nvtabular, I have the following in my workflow Col1 ; Col2...

amulyahwr

[QST] Accessing the model architectures separately.

1

Similar HuggingFace Transformers is there a way to import model architectures and explore them. from transformers import BertModel, BertConfig ``` # Initializing a BERT bert-base-uncased style configuration configuration = BertConfig()...

shamanez