Text Classification
PEFT
lora
document-question-answering
structured-decisions
calibration
synthetic-evaluation
Instructions to use botp/Solomon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use botp/Solomon with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| from solomon_mlx import Solomon | |
| model = Solomon.load("models/quality") | |
| questions = { | |
| "certified": {"type": "noul", "instructions": "Is Rookwood Ltd certified?"}, | |
| "auditor": { | |
| "type": "choice", | |
| "instructions": "Who performs the audit?", | |
| "options": ["The Buyer", "The grower", "An independent auditor"], | |
| }, | |
| "severity": { | |
| "type": "score", | |
| "instructions": "What is the breach severity?", | |
| "levels": ["none recorded", "minor", "material"], | |
| }, | |
| } | |
| with model.prefill( | |
| "Rookwood Ltd is certified. An independent auditor performs the audit. One minor breach is recorded." | |
| ) as state: | |
| print(model.decide(state=state, questions=questions, evidence="support")) | |
| state.save("document-replay.json") | |