README.md

---
license: apache-2.0
language:
- en
tags:
- control-vector
- creative-writing
---

## gghfez/L3.3-70B-Euryale-v2.3-control-vectors

Creative Writing control-vectors for [Sao10K/L3.3-70B-Euryale-v2.3](https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3)

## Usage example

### llama.cpp
```sh
llama-server --model  L3.3-70B-Euryale-v2.3.Q5_K_M.gguf [other CLI arguments] \
    --control-vector  L3.3-70B-Euryale-v2.3-character_focus__debias.gguf \
    --control-vector  L3.3-70B-Euryale-v2.3-character_focus__dialogue.gguf
```

### exllamav2 with exui (via exui fork)

https://github.com/gapeleon/exui-control-vectors

1. Set it up / install it the same as regular exui
2. `pip install gguf` if you don't have it already
3. Create a directory alongside the model but with `-vectors` appended
4. Start exui `python server.py`
5. When setting up the model on the model config page, add the vectors and their scaling/direction then click "load model"
6. 
Trained on 1xH100NVL using jukofyork's [control-vectors](https://github.com/jukofyork/control-vectors)

Based off Version v3.0 of [creative-writing-control-vectors-v3.0](https://huggingface.co/jukofyork/creative-writing-control-vectors-v3.0/).

See here for more info about control-vectors [creative-writing-control-vectors-v3.0](https://huggingface.co/jukofyork/creative-writing-control-vectors-v3.0/)