Transformers4Rec
Transformers4Rec copied to clipboard
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
### Description Provide support for pretrained embeddings passed from the data loader ### Goals - [ ] Update the [input block](https://github.com/NVIDIA-Merlin/Transformers4Rec/blob/21a2a836a30610746bc8788ff926bad74fd00289/transformers4rec/torch/features/sequence.py#L97) to support the pre-trained embeddings: - Add a module...
# 🚀 Feature request Update Transformers4Rec to use the latest version of HF transformers. ## Motivation The current API supports a pinned old version (4.12.*) while the latest HF (4.25.*)....
Hello. I've adapted t4rec model to my own e-commerce dataset and trained it but the model is not capturing the relationships between products and not giving a logical results. For...
### Bug description The `clm` masking for last item only do not mask last item in input. It will cause using the embedding of the **label** instead of **mask**. I...
### Bug description I'm trying to run the example notebook with synthetic data [getting-started-session-based](https://github.com/NVIDIA-Merlin/Transformers4Rec/tree/main/examples) and I'm getting the following error ``` --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) Cell In[21],...
Tried to run the tutorial of transformers4rec and i got this error --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in [/usr/local/lib/python3.10/dist-packages/transformers/trainer.py](https://localhost:8080/#) in evaluate(self, eval_dataset, ignore_keys, metric_key_prefix) 3005 self._memory_tracker.start() 3006 ->...
# ❓ Questions & Help ## Details I'm currently using the Transformers4Rec for a Next Item Prediction task. I've successfully pre-trained my model, and now I wish to extract user...
# 🚀 Feature request https://github.com/NVIDIA-Merlin/competitions/blob/3734d8aef94c73f5f8a572789aca1a17f69b12a5/SIGIR_eCommerce_Challenge_2021/task1_session_based_rec/2-models/sigir_ecom_transformers/recsys_meta_model.py#L605 ## Motivation SIGIR_eCommerce_Challenge_2021 solution from nvidia used a post-context fusion of search embeddings. Is there a way to introduce post context fusion using t4rec api...
# ❓ Questions & Help ## Details I have two separate sequences and want to create two towers and then concat the output layers of two transformer towers. Can you...
# ❓ Questions & Help ## Details Hello! I'm working on an e-commerce dataset to predict items. I successfully run the training of the model in the tutorial and now...