Text Classification
Transformers
Safetensors
English
basedecision_dyno
feature-extraction
decision-model
system-one
decision-index
multiple-choice
calibration
read-twice
custom-code
lora-merged
custom_code
Instructions to use onlyaady/BaseDecision-Dyno with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use onlyaady/BaseDecision-Dyno with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="onlyaady/BaseDecision-Dyno", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("onlyaady/BaseDecision-Dyno", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
15 days ago
-
Publish calibrated BaseDecision-Dyno with portable HTTP serving
Verified signatureREADME unchanged. No backup branch or tag created. Native weights and scoring code unchanged; public names and serving instructions updated. Default is calibrated read twice; flash requires explicit selection. Calibration passed the declared historical holdout audit; the Noul subset regressed slightly. No new public benchmark or JevBench score is claimed.3e88dcc -
Release BaseDecision-Dyno v2: real-data lr1e6, default read twice
Verified signaturePreserves the previous revision by tag. Source adapter public index 54.80; T=1.0, uncalibrated. Includes a TypeSafe-wire HTTP server for evaluator review; not yet an approved JevBench adapter.fc43746
18 days ago
-
Release calibrated BaseDecision-Dyno with default read twice
Verified signature4c87263