Text Classification
Transformers
Safetensors
Chinese
spam-detection
advertising-detection
chinese
modernbert
multi-task
four-head
Instructions to use x6nux/laya-ad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use x6nux/laya-ad with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="x6nux/laya-ad")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("x6nux/laya-ad", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
Yesterday
-
发布 v2.3:v25 四头模型、六精度与发布前性能测试
Verified signatureFP32 weights are byte-identical to local training run v25. Includes six precision variants, fixed-threshold regression metrics, agreement checks and GPU forward benchmarks. No training corpora or credentials included.c03e108
21 days ago
-
README: 路由说明改为四头口径(scope/severity 头)
Verified signaturec4a7829 -
README: 指标说明(测试集来源、每个指标定义与读法、四头对应的生产决策)
Verified signature13ed2f5 -
laya-ad v2.2: sync laya-server code (default version v2.2, build_push.sh, .env.example)
Verified signature0cd599e -
laya-ad v2.2: six precision dirs
Verified signaturee2492ec
22 days ago
-
laya-ad v2.1: six precision dirs
Verified signaturef8d2531 -
chore: remove __pycache__ from v2 code
Verified signature89a7d3a -
laya-ad v2: one dual-head model (binary + 7-class kind), six precision dirs
Verified signaturedd18e84
23 days ago
-
laya-ad v1.1:六精度权重 + 模型卡 + 项目代码快照
Verified signature71dabc7 -
initial commit
Verified signature5a91bef