from transformers import pipeline
decide = pipeline("decision", model="jaredpalmer/kev-4b", decision_config="ArthurZ/kev-4b")
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/
:
KevDecisionHead
, converted from
head.pt
of the original.
decision_test.json
: a request and the input ids that the original code builds for it, used by the tests.
kev-4b huggingface.co is an AI model on huggingface.co that provides kev-4b's model effect (), which can be used instantly with this ArthurZ kev-4b model. huggingface.co supports a free trial of the kev-4b model, and also provides paid use of the kev-4b. Support call kev-4b model through api, including Node.js, Python, http.
kev-4b huggingface.co is an online trial and call api platform, which integrates kev-4b's modeling effects, including api services, and provides a free online trial of kev-4b, you can try kev-4b online for free by clicking the link below.
kev-4b is an open source model from GitHub that offers a free installation service, and any user can find kev-4b on GitHub to install. At the same time, huggingface.co provides the effect of kev-4b install, users can directly use kev-4b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.