Darwin-27B-ZTC for 🤗 Transformers

The 255-way answer-code readout of FINAL-Bench/Darwin-27B-ZTC as a JEV decision head, for the decision pipeline. This repo holds the readout, the tokenizer and the prompt; the backbone loads from the original repo.

Questions

Each question is answered with a probability for every option: noul (yes/no), choice and score.

from transformers import pipeline

decide = pipeline("decision", model="ArthurZ/Darwin-27B-ZTC")
answers = decide(
    {
        "state": {"customer": "Lena", "message": "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?"},
            "tone": {"type": "choice", "instructions": "What is the tone?", "criteria": {"calm": "Polite", "angry": None}},
            "urgency": {"type": "score", "instructions": "How urgent is it?", "criteria": ["Can wait", "This week", "Today", "Now"]},
        },
    }
)
answers["refund"]["noul"]  # probability of true
answers["tone"]["choice"], answers["tone"]["probabilities"]
answers["urgency"]["score"]  # expected level, 0 to 3

Same questions, new states

A bare state is asked the questions of the last request, or the ones given up front:

decide = pipeline(
    "decision",
    model="ArthurZ/Darwin-27B-ZTC",
    questions={"spam": {"type": "noul", "instructions": "Is this spam?"}},
)
decide("WIN A FREE IPHONE!!! click here to claim your prize")
decide("Hi! The parcel arrived, thanks a lot.")

Converted with convert_decider_to_hf.py. Its prompts are token-for-token those of the original code (decision_test.json), except that control tokens written in a request are escaped instead of read as such.