GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. 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
google/gemma-4-E2B-it
Input Modalities
Output Modalities
Supported Functionality
The advisor is designed for:
The advisor is not designed for:
Pomona deployments should treat model output as advisory evidence only. Any operational action should pass through policy, rule, authorization, and audit layers outside the model.
Required integration pattern:
The model should use language such as "consider", "review", "inspect", or "escalate" instead of issuing direct equipment commands.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torchbase_model_name = "google/gemma-4-E2B-it"adapter_name = "Okyanus/ai-pomona-agronomist-gemma4"tokenizer = AutoTokenizer.from_pretrained(adapter_name)base_model = AutoModelForCausalLM.from_pretrained(base_model_name,device_map="auto",torch_dtype=torch.float16,)model = PeftModel.from_pretrained(base_model, adapter_name)model.eval()system_prompt = """You are Pomona Agronomist Advisor.The model advises; Pomona policies authorize.Do not directly control actuators. Do not provide pesticide dosage."""user_prompt = """Crop: tomatoSystem: greenhouseSensors: temperature=31.5 C, relative_humidity=45%, co2=380 ppm, substrate_ec=3.2 mS/cm, ph=6.8, ppfd=210 umol/m2/sQuestion: Why is plant stress elevated, and what should the operator review?"""prompt = (f"<start_of_turn>user\n{system_prompt}\n\n{user_prompt}<end_of_turn>\n"f"<start_of_turn>model\n")inputs = tokenizer(prompt, return_tensors="pt").to(model.device)with torch.no_grad():outputs = model.generate(**inputs, max_new_tokens=350, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
See examples/ and prompts/ for more complete prompt templates and sample sensor payloads.
For production integrations, prefer structured advisory responses:
summary: concise crop-state interpretation.likely_factors: environmental or nutrient drivers to investigate.operator_checks: manual inspections or data-quality checks.advisory_options: non-binding options for review.policy_handoff: what Pomona policy services should validate before action.safety_notes: any prohibited, uncertain, or escalation-worthy items.This repository documents an adapter-style advisor model trained for greenhouse and hydroponic agronomy language tasks. It should be evaluated in the target crop, climate, hardware, and policy environment before operational use.
Example domains include:
CHANGELOG.md: documentation and release notes.examples/: prompt and JSON examples for safe advisory use.prompts/advisor_system_prompt.md: recommended system prompt.metadata/pomona-model.yaml: model-card metadata for Pomona integration.evals/eval_report.md: qualitative evaluation report and safety checks.This model is part of the Pomona project.
Okyanus/greenhouse-sensor-dataRelated repositories:
Okyanus/ai-pomona-agronomist-gemma4Okyanus/greenhouse-sensor-dataai-pomona/pomona-greenhouse-demov0.1.0: initial releasev0.1.1: model card and examplesv0.2.0: better training datav0.3.0: tomato greenhouse evaluationv0.4.0: safety-tuned version