NVIDIA-Merlin/Transformers4Rec

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

Stars: 1.3k
Forks: 165
Open beginner issues: 5
Indexed issues: 97
Avg merge: 1m
Merged PRs (30d): 2

Dominant language: Python
License: Apache-2.0
Last GitHub push: Aug 23, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue

Beginner friendly Everything

Open All

5 beginner-friendly issues open

[BUG] `Head._task_weights = defaultdict()` silently behaves like a plain dict Open

Difficulty 1/5 Under an hour Newbie friendliness 74/100

NVIDIA-Merlin/Transformers4Rec#813 · Opened Apr 17, 2026
[BUG] `MerlinDataLoader._augment_schema` raises TypeError when `lists` is omitted Open

Difficulty 1/5 Under an hour Newbie friendliness 88/100

NVIDIA-Merlin/Transformers4Rec#812 · Opened Apr 17, 2026
[BUG] `Head.build` raises `TypeError: 'NoneType' object is not callable` when body lacks `output_size` Open

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

NVIDIA-Merlin/Transformers4Rec#811 · Opened Apr 17, 2026
[BUG] `Model.load` raises TypeError on Python 3.9+ (parameterized generic in isinstance) Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

NVIDIA-Merlin/Transformers4Rec#810 · Opened Apr 17, 2026
[BUG] `load_model_trainer_states_from_checkpoint()` function is broken Open

bug status/needs-triage

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

NVIDIA-Merlin/Transformers4Rec#806 · 1 comment · Opened Jan 18, 2026

A short digest of beginner-friendly GitHub issues.