Escarda-Rewrite (86M)

86M prompt optimizer. Raw question in, detailed role-grounded instruction prompt out - persona, task framing, clarifying questions.

Escarda line (JEPA SpikeWhale, vocab 16,512). Meant to sit in front of Quazim0t0/Escarda-86M-Identity:

user query → Escarda-Rewrite → optimized prompt → Escarda-Identity → answer.

Example

Raw query	Escarda-Rewrite output
How do I lower my cholesterol?	As a Senior Medical Expert, your task is to provide clear, concise guidance on lowering cholesterol… Begin by declaring your persona… Next, ask clarifying questions…
How do I grow tomatoes?	As an Agricultural Scientist, your task is to provide clear guidance on growing tomatoes… Begin by introducing yourself…
What are my rights if I am fired?	As a Senior Legal Advisor, your task is to provide guidance on… Begin by declaring your persona…

Usage

from rewrite import EscardaRewrite
rw = EscardaRewrite(".")            # loads model + tokenizer from this repo
print(rw.rewrite("How do I lower my cholesterol?"))

How it was built

Trained to match, and benchmarked against, QueryShield-1.5B (ml-intern-explorers/queryshield-1.5b) - a 1.5B prompt optimizer - at ~1/17th the size. Balanced topic-roled corpus so the expert persona tracks the query (Medical, Legal, Financial, Agricultural, Software, Data Science, Marketing, Education, Research, …).

Citation

Created by Dean Byrne (Quazim0t0).

@misc{byrne2026escardarewrite,
  title  = {Escarda-Rewrite: an 86M prompt optimizer},
  author = {Byrne, Dean},
  year   = {2026}
}