models

models copied to clipboard

### Description Add integration test when the jenkins machine has the dataset. More information [here](https://github.com/NVIDIA-Merlin/models/pull/629#discussion_r942206875)

radekosmulski

[Task] Update the high-level API of retrieval models with new core API

1

# 🚀 Feature request The objective is to update retrieval models with the new core API classes once they are completed and tested. The feature includes updating the code base...

sararb

Unify the name of merlin models logger

1

🗒️ this doesn't need to be addressed in this PR. This is an observation that we should address the inconsistency we have in the name we used inside `getLogger` across...

sararb

[BUG]Flaky unit tests for models

2

### Bug description Unit tests failed for models in this run https://blossom.nvidia.com/sw-gpu-merlin-ci/job/new-test-merlin/717/ This may be due to a flaky unit test. This must be checked in 22.08.

viswa-nvidia

[FEA] Add a warning, if embedding tables are not used in merlin models

1

# 🚀 Feature request As a user, I can provide custom configs to the embedding_initalizer. However, the input data schema does not tag the column names as ITEM / USER...

bschifferer

[BUG] to_top_k_recommender model does not have batch_predict() method

1

### Bug description I'd like to apply [batch_predict()](https://github.com/NVIDIA-Merlin/models/blob/main/merlin/models/tf/models/base.py#L588) to `top_k_recommender` model but it gives the following error: ``` topk_rec_model.batch_predict() --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) Input In [17], in...

rnyak

# 🚀 Feature request Currently it is hard to map the variables and ops in the TF graph generated by Merlin Models to the corresponding Blocks. We should organize Blocks'...

gabrielspmoreira

### Description The team had discussions on porting Transformers4rec to Merlin Models and supporting the model in Triton inference server as one of the goals for 22.09. However, there needs...

edknv

"05-Retrieval-Model.ipynb" - how to feed multiple train files, and generate prediction in triton [QST]

1

# ❓ Questions & Help ## Details In this example - https://github.com/NVIDIA-Merlin/models/blob/main/examples/05-Retrieval-Model.ipynb, if I use "workflow.fit_transform(dataset).to_parquet(output_path="./processed/", shuffle=shuffle, out_files_per_proc=10)",to generate 10 train files to avoid OOM error, can I just simply...

lightsailpro

## Motivation Training with masked input sequences has proven very effective for session-based and sequential tasks (Bert4Rec, SaSRec, and Transformers4Rec). As a first step towards integrating sequential models, Merlin Models...

sararb