GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Okyanus
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Okyanus
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This model is part of Pomona's small-model factory experiment: instead of relying on one large general-purpose LLM for every agriculture task, Pomona trains compact specialists for narrow, verifiable jobs and wraps them with deterministic safety logic.
This direction is inspired by recent small-reasoner work such as:
Pomona does not use VibeThinker code, weights, or training data. The connection is conceptual: VibeThinker-style work suggests that small models can become useful when the task is narrow, the output is verifiable, and evaluation is strict. Pomona applies that idea to agriculture by pairing a small LoRA reasoner with deterministic tomato safety rules.
In this release, the small model handles the learned risk-label classification behavior, while Pomona's rule checker enforces hard thresholds for missing data, impossible sensor values, water risk, fungal pressure, and actuator conflicts.
Qwen/Qwen2.5-0.5B-Instructjson
[ "high_ph", "low_ph", "high_ec", "low_ec", "heat_stress", "cold_stress", "fungal_pressure", "nutrient_uptake_issue", "sensor_anomaly", "missing_critical_data", "water_level_risk", "actuator_conflict"]text
sensor input -> v0.1.7 adapter predicts risk labels -> Pomona deterministic rule checker validates/corrects labels -> guarded hybrid output is used by API/dashboardDo not use this adapter for direct pesticide dosage, autonomous fertigation changes, direct actuator control, definitive disease diagnosis, or unsafe chemical recommendations.
json
{ "system_type": "controlled_greenhouse", "crop": "tomato", "growth_stage": "flowering", "air_temperature_c": 24.0, "humidity_pct": 89.0, "co2_ppm": 600, "light_ppfd": 350, "ph": 6.2, "ec_ms_cm": 2.4, "water_temperature_c": 21.0, "substrate_temperature_c": 23.0, "substrate_moisture_pct": 45.0, "actuator_states": { "screen_energy_pct": 90 }, "symptoms": []}Expected guarded Pomona output:
json
["fungal_pressure", "actuator_conflict"]Clone the platform and run the guarded route end to end — no extra dependencies, no private files required:
bash
git clone https://github.com/okyanu/pomona.gitcd pomonacp .env.example .env./scripts/up.sh python3 examples/tomato_risk_quickstart.pyRuntime status: local Ollama inference for this adapter is wired into
the platform (schema-constrained JSON decoding via format in the Ollama
/api/chat request, so the model can only emit valid label lists), but it
is off by default (REASONER_BACKEND=rules). Enable it with
REASONER_BACKEND=ollama once pomona-tomato-risk:v0.1.7-local is built
and running locally — see
docs/LOCAL_MODEL_RUNTIMES.md
in the platform repo. Even with it enabled, hybrid_guarded mode validates
the model's output but keeps the deterministic rules as the final decision;
only model_only (evaluation) mode surfaces raw model output, currently at
0.60 label F1 on the 15-case golden smoke suite — well below the rules'
1.0, which is why the guardrail stays authoritative.
Best standalone adapter from the local iteration:
text
v0.1.7 staged risk F1: 0.924 on its original staged testv0.1.7 golden risk F1: 0.667Hybrid guarded evaluation with Pomona deterministic tomato rules:
text
golden eval: model-only risk F1: 0.667 hybrid risk F1: 1.000 corrections: 5 / 15 v0.1.7 staged test: model-only risk F1: 0.902 hybrid risk F1: 1.000 corrections: 59 / 473The hybrid score is measured on a rule-derived eval set, so it should be interpreted as a guardrail integration check, not as an independent real-world agronomy benchmark. Future releases should add human-reviewed field cases.
This adapter is one small specialist in the Pomona small-model factory:
text
small task model + deterministic safety rules = practical local AI componentThe platform repository keeps code, schemas, docs, and rule logic. Hugging Face stores model adapter weights.
If you discuss the design motivation, cite the VibeThinker papers as related small-reasoner inspiration, not as the source of this model:
bibtex
@article{xu2025vibethinker15b, title = {Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B}, author = {Xu, Sen and Zhou, Yi and Wang, Wei and Min, Jixin and Yin, Zhibin and Dai, Yingwei and Liu, Shixi and Pang, Lianyu and Chen, Yirong and Zhang, Junlin}, journal = {arXiv preprint arXiv:2511.06221}, year = {2025}} @article{xu2026vibethinker3b, title = {VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models}, author = {Xu, Sen and Liu, Shixi and Wang, Wei and Min, Jixin and Dai, Yingwei and Yin, Zhibin and Chen, Yirong and Zhou, Xin and Zhang, Junlin}, journal = {arXiv preprint arXiv:2606.16140}, year = {2026}}[ "high_ph", "low_ph", "high_ec", "low_ec", "heat_stress", "cold_stress", "fungal_pressure", "nutrient_uptake_issue", "sensor_anomaly", "missing_critical_data", "water_level_risk", "actuator_conflict"]sensor input -> v0.1.7 adapter predicts risk labels -> Pomona deterministic rule checker validates/corrects labels -> guarded hybrid output is used by API/dashboard{ "system_type": "controlled_greenhouse", "crop": "tomato", "growth_stage": "flowering", "air_temperature_c": 24.0, "humidity_pct": 89.0, "co2_ppm": 600, "light_ppfd": 350, "ph": 6.2, "ec_ms_cm": 2.4, "water_temperature_c": 21.0, "substrate_temperature_c": 23.0, "substrate_moisture_pct": 45.0, "actuator_states": { "screen_energy_pct": 90 }, "symptoms": []}git clone https://github.com/okyanu/pomona.gitcd pomonacp .env.example .env./scripts/up.sh python3 examples/tomato_risk_quickstart.pygolden eval: model-only risk F1: 0.667 hybrid risk F1: 1.000 corrections: 5 / 15v0.1.7 staged test: model-only risk F1: 0.902 hybrid risk F1: 1.000 corrections: 59 / 473@article{xu2025vibethinker15b, title = {Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B}, author = {Xu, Sen and Zhou, Yi and Wang, Wei and Min, Jixin and Yin, Zhibin and Dai, Yingwei and Liu, Shixi and Pang, Lianyu and Chen, Yirong and Zhang, Junlin}, journal = {arXiv preprint arXiv:2511.06221}, year = {2025}} @article{xu2026vibethinker3b, title = {VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models}, author = {Xu, Sen and Liu, Shixi and Wang, Wei and Min, Jixin and Dai, Yingwei and Yin, Zhibin and Chen, Yirong and Zhou, Xin and Zhang, Junlin}, journal = {arXiv preprint arXiv:2606.16140}, year = {2026}}