| ---
|
| 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
|
|
|
| ```bash
|
| 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.
|
|
|
