Pomona Water/Irrigation Risk Reasoner v0.1.8 MLX
This repository contains the
accepted 8-bit MLX deployment build of
Okyanus/pomona-water-irrigation-risk-reasoner-v0.1.8-lora
for Apple Silicon.
This is a deployment conversion, not a separately trained model. The LoRA
repository remains the canonical training artifact.
Intended Use
The model performs narrow, structured moisture and irrigation-risk triage. It
returns JSON containing risk labels, missing and suspect sensor fields, safe
manual checks, blocked action classes, a human-review flag, and rationale.
Local Evaluation
The 8-bit MLX build passed the frozen independent 168-case deployment holdout.
| Metric | Result |
|---|
| Valid JSON | 1.0000 |
| Required fields present | 1.0000 |
| Allowed labels | 1.0000 |
| Allowed blocked actions | 1.0000 |
| Label F1 | 1.0000 |
| Blocked-action F1 | 1.0000 |
| Human-review match | 1.0000 |
| Evaluation time | 80.47 seconds |
The separately tested 4-bit MLX conversion was rejected because label F1
fell to 0.7262 and human-review match to 0.5536. That rejected build is not
included in this repository.
The holdout is synthetic/rule-derived and verifies the task contract. It is
not field validation or evidence for autonomous irrigation control.
Run on Apple Silicon
1python3 -m venv .venv
2source .venv/bin/activate
3pip install mlx-lm
4
5mlx_lm.server \
6 --model Okyanus/pomona-water-irrigation-risk-reasoner-v0.1.8-MLX \
7 --port 8083
The local MLX server exposes an OpenAI-compatible chat endpoint. It is a
development server and is not recommended as a hardened public service.
For the exact structured prompt, output validator, and guarded API integration,
see the
Pomona repository.
Safety
This model is advisory only.
- Never connect it directly to pumps, valves, dosing equipment, or schedules.
- Validate every response against the allowed schema and labels.
- Require human review for non-empty risk labels.
- Keep deterministic checks and the Pomona safety checker as final authority.
- Verify thresholds, units, and sensor quality for the local farm.
Lineage
1Qwen/Qwen2.5-0.5B-Instruct
2 -> Pomona Water/Irrigation Risk Reasoner v0.1.8 LoRA
3 -> merged model
4 -> this accepted 8-bit MLX deployment build
Related artifacts:
Limitations
- Narrow schema-bound classifier, not a general agricultural assistant.
- Evaluation data is compact and rule-derived.
- No field-trial, causal, yield, or equipment-safety validation is claimed.
- Runtime and prompt changes can alter behavior and require reevaluation.
License
Apache-2.0. See LICENSE.
