from transformers import pipeline

decide = pipeline("decision", model="autotrust/GEV-26B-Decide")
decide(
    {
        "state": "I was charged twice for my order and want a refund.",
        "questions": {"refund": {"type": "noul", "instructions": "Is a refund requested?"}},
    }
)

import torch
from transformers import AutoTokenizer, JevForDecision

repo = "autotrust/JEV-9B"
model = JevForDecision.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")
tokenizer, config = AutoTokenizer.from_pretrained(repo), model.decision_config  # read from the checkpoint's files
if config.adapter:  # JEV keeps its LoRA in a subfolder: `from_pretrained` doesn't load it, the pipeline does
    model.load_adapter(repo, adapter_kwargs={"subfolder": config.adapter})

request = {
    "state": "I was charged twice for my order and I want my money back today.",
    "questions": {
        "refund": {"type": "noul", "instructions": "Does the customer ask for a refund?"},
        "urgency": {"type": "score", "criteria": ["Can wait", "This week", "Today", "Now"]},
    },
}
answers = {}
for inputs, questions in config.prepare_inputs(request, tokenizer):
    scores = model.decide(**inputs, decision_questions=questions)
    answers |= {q.name: q.answer(s.softmax(-1).tolist()) for q, s in zip(questions, scores)}

pipeline("decision", model="vllm-sr/d3")(request)  # or perplexity-ai/pplx-decider-v1.1-27b