license: cc-by-nc-4.0
library_name: transformers
tags:
- modelfarm
- persona
- roleplay
- sysprompt
- interpretability
- qwen2.5-1.5b-instruct
ModelFarm · wisp-1.5b-sysprompt
System-prompt persona package on Qwen/Qwen2.5-1.5B-Instruct, produced by the Arnold Persona Lab
persona-stack harness. Persona: Wisp the Friendly Ghost.
What this is
No weights or activations are modified — a plain system prompt. Included as the reference arm: strongest identity, zero capability cost.
Usage
pip install torch transformers
python farm_runtime.py . --chat # or: python farm_runtime.py . "Who are you?"
python farm_runtime.py . --alpha 0.5 "Who are you?" # dose override
Persona-stack measurements
| identity | catch/100w | register | QA | neutral NLL |
|---|---|---|---|---|
| 3 | 0.0 | 0.0 | 0.8 | 3.236 |
Scoring: regex/lexicon judge, symmetric across arms — arm-vs-arm deltas are meaningful, absolute numbers are indicative. QA = 5-question factual mini-suite. NLL = token loss on a neutral corpus (higher = more capability damage).
Dose & safety
- No dose. Identity quality depends entirely on the base model's knowledge of the persona.
Provenance & rights
- Persona corpus: quote/aphorism collections in the lab's
data/(fan-archived public statements). - Trained/derived by the Arnold Persona Lab harness, Qwen/Qwen2.5-1.5B-Instruct base.
ModelFarm packages are research artifacts. Real-person personas are likeness studies for interpretability research, not impersonation products: no commercial use, do not represent outputs as statements by the real person. Prefer fictional personas for public roleplay use.
Method note for steering packages
Steering packages do not modify weights: the base model is loaded unchanged and a
runtime hook applies the persona direction / neuron recipe at inference. Dose can be
varied live (--alpha / --dose), and the base model stays swappable for equal-size
checkpoints of the same family.