Text Classification
Transformers
Safetensors
Japanese
sokudan
japanese
system-one
calibrated-decisions
classification
routing
ordinal
model-soup
Instructions to use GeneLab/sokudan-ja-310m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GeneLab/sokudan-ja-310m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GeneLab/sokudan-ja-310m")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GeneLab/sokudan-ja-310m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
27 days ago
-
card: sokudan 0.3.0 (MLX, Python 3.11-3.13, catch-all limits, bench license wording)
Verified signature3e3409b
28 days ago
-
Model card: pip install sokudan (PyPI 0.2.1), git+ as the development version, Colab notebook link
Verified signature5f91a0d -
v0.2.1: bool calibration (calibration.json, bool/2 only) and model card; weights unchanged
Verified signaturebb09c20
30 days ago
-
v0.2: model soup of v0.1 seeds 0-7 (v0.1 stays as revision v0.1)
Verified signatureWeights: plain average of eight v0.1-recipe checkpoints (seeds 0-7). model.safetensors SHA-256 8750a833b3faa537a39709b8377b82a096286f040d78bb1915b82d9d101b5965. Code: https://github.com/hiroki-abe-58/sokudan (tag v0.2).6cfe939
-
Model card: condition F, English reproduction, link to laya#259; absolute links in Limits
Verified signature10d80cd
-
sokudan-ja-310m v0.1 (3 seeds)
Verified signatureb16df2b
-
sokudan-ja-310m v0.1 (3 seeds)
Verified signatureefe7177 -
sokudan-ja-310m v0.1 (3 seeds)
Verified signature3426824 -
initial commit
Verified signature1c8ed34