Downloads · 30 days
0
newsrex/NAML-JAX-MIND-small-glove-random
NAML-JAX-MIND-small-glove-random is a machine learning model from newsrex. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for newsrex. The card lists the license as apache-2.0.
NAML news recommendation model trained on MIND-small using the NewsReX framework (JAX).
Downloads · 30 days
0
Access
Public
Updated Jun 6, 2026
Parameters
20.5M
246 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors327 MB · 100%
How the weights are stored.
F3215.1M · 74%
From the Hugging Face model README
NAML news recommendation model trained on MIND-small using the NewsReX framework (JAX).
| Seed | AUC | MRR | NDCG@5 | NDCG@10 |
|---|---|---|---|---|
| 123 | 0.6512 | 0.3023 | 0.3342 | 0.3966 |
| 42 * | 0.6520 | 0.3031 | 0.3335 | 0.3980 |
| 456 | 0.6456 | 0.3017 | 0.3324 | 0.3958 |
| mean ± std | 0.6496±0.0028 | 0.3024±0.0006 | 0.3334±0.0007 | 0.3968±0.0009 |
* Best seed (weights at repo root)
model:
name: naml
architecture:
news_encoder:
type: cnn_multi_view
views:
title:
type: cnn
filter_num: 400
kernel_size: 3
activation: relu
attention_query_dim: 200
abstract:
type: cnn
filter_num: 400
kernel_size: 3
activation: relu
attention_query_dim: 200
category:
type: embedding
embedding_dim: 100
subcategory:
type: embedding
embedding_dim: 100
view_attention_query_dim: 200
user_encoder:
type: additive_attention
attention_query_dim: 200
num_attention_heads: 10
click_predictor:
type: dot_product
embedding:
size: 300
trainable: true
dropout_rate: 0.2
seed: 42
inputs:
title:
max_length: 32
abstract:
max_length: 50
history:
max_length: 50
impressions:
max_length: 5
process_title: true
process_abstract: true
process_category: true
process_subcategory: true
process_user_id: false
training:
loss:
name: categorical_crossentropy
from_logits: true
reduction: sum_over_batch_size
label_smoothing: 0.0
optimizer: adam
learning_rate: 0.0001
batch_size: 256
num_epochs: 10
early_stopping:
patience: 3
min_improvement: 0.01
negative_sampling:
strategy: random
candidates: 4
evaluation:
mode: fast
metrics:
- auc
- mrr
- ndcg@5
- ndcg@10
batch_size: 512
newsrex/NAML-JAX-MIND-small-glove-random/
├── model.safetensors ← best seed (42)
├── test_results.json
├── training_run_summary.json
├── seed_123/model.safetensors
├── seed_42/model.safetensors
├── seed_456/model.safetensors
└── README.md
git clone https://github.com/igor17400/NewsReX.git
cd NewsReX && uv sync
# Run evaluation with best seed weights
uv run python src/eval.py \
experiment=mind/glove/naml \
framework=jax \
weights=hf://newsrex/NAML-JAX-MIND-small-glove-random/model.safetensors
# Run evaluation with a specific seed
uv run python src/eval.py \
experiment=mind/glove/naml \
framework=jax \
weights=hf://newsrex/NAML-JAX-MIND-small-glove-random/seed_42/model.safetensors
@misc{newsrex2026,
title={NewsReX: An Open-Source Multi-Framework for Neural News Recommendation},
author={Igor L. R. Azevedo and Toyotaro Suzumura and Yuichiro Yasui},
year={2025},
eprint={2508.21572},
archivePrefix={arXiv},
primaryClass={cs.IR},
url={https://arxiv.org/abs/2508.21572},
}