Controlled_Chat_CPU / README.md
abrakjamson
Adding readme (and missing control model)
2fd6955
|
raw
history blame
677 Bytes
---
title: LLM Mind Control
emoji:
colorFrom: pink
colorTo: gray
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
preload_from_hub:
- mistralai/Mistral-7B-Instruct-v0.3
suggested_hardware:
- l4x1
---
# 🧠 LLM Mind Control"
Unlike prompting, direct weight manipulation lets you fine-tune the amount of a personality
trait or topic. Enabled through [Representation Engineering](https://arxiv.org/abs/2310.01405)
via the [repeng](https://pypi.org/project/repeng) library.
[Watch a demo](https://youtu.be/gYZPGVafD7M) for usage tips.
This space needs more than 16GB of video memory to run on GPU, but could be modified to use a smaller model.