wfzyx/von: decision files

Chat template, settings and head of wfzyx/von for pipeline("decision") (transformers#49566). The backbone stays the original checkpoint.

from transformers import pipeline

decide = pipeline("decision", model="wfzyx/von", decision_config="ArthurZ/von")
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/: VonDecisionHead, converted from option_marker.pt 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 wfzyx/von (Apache-2.0).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ArthurZ/von

Finetuned
wfzyx/von
Finetuned
(3)
this model