Text Classification
PEFT
lora
document-question-answering
structured-decisions
calibration
synthetic-evaluation
Instructions to use DoccyHealth/Solomon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use DoccyHealth/Solomon with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Archer
Claude Opus 5 (1M context)
Solomon v1.1: BF16 default, fp32 reference and int8 option, ranked evidence pointers, entity type removed
d144fee | { | |
| "adapter_sha256": "d122466d430a058bb6457d919f811160e97fbd20149f4f24ca455c5d83e360a0", | |
| "binding": "serving-binding.json", | |
| "contract": "solomon-v1", | |
| "design": { | |
| "ordered": "S", | |
| "single_choice": "R" | |
| }, | |
| "evidence_head": { | |
| "prefix": "evidence-head", | |
| "thresholds": "evidence-policy.json" | |
| }, | |
| "frozen": true, | |
| "heads_sha256": "f766d752d7768a419a9657155cf27f042834d9de29392cf7470d8725130e67ab", | |
| "note": "readout mode, served design, the default (bf16) serving binding and the evidence head, named relative to this file. The binding pins the full runtime identity. For fp32 or int8 serving, pass the matching serving-binding-<precision>.json and build the engine with that precision.", | |
| "readout": "four_collapsed", | |
| "readout_mode": "four_collapsed", | |
| "schema": "solomon-selection-v1" | |
| } | |