ArthurZ / JEV-9B

autotrust/JEV-9B: decision files

Chat template, settings and head of autotrust/JEV-9B for pipeline("decision") ( transformers#49566 ). The backbone is the base model at the root of the original with the System 1 LoRA of the original ( adapter_model.safetensors ), loaded by from_pretrained .

from transformers import pipeline

# the LoRA at the root makes `pipeline` load its base model, so the decision files are passed explicitly
decide = pipeline("decision", model="ArthurZ/JEV-9B", decision_config="ArthurZ/JEV-9B")
decide({"state": "I was charged twice and want a refund.", "questions": {"refund": {"type": "noul", "instructions": "Is a refund requested?"}}})

• decision_template.jinja : the chat template; <|mark|> marks the positions the head reads.
• decision_config.json : temperatures and option order.
• decision_head/ : JevDecisionHead , converted from head.safetensors of the original.
• decision_test.json : a request and the input ids that the original code builds for it, used by the tests.

Derived from autotrust/JEV-9B (Apache-2.0).