Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- control-vector
|
7 |
+
- creative-writing
|
8 |
+
---
|
9 |
+
|
10 |
+
## gghfez/L3.3-70B-Euryale-v2.3-control-vectors
|
11 |
+
|
12 |
+
Creative Writing control-vectors for [Sao10K/L3.3-70B-Euryale-v2.3](https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3)
|
13 |
+
|
14 |
+
## Usage example
|
15 |
+
|
16 |
+
### llama.cpp
|
17 |
+
```sh
|
18 |
+
llama-server --model L3.3-70B-Euryale-v2.3.Q5_K_M.gguf [other CLI arguments] \
|
19 |
+
--control-vector L3.3-70B-Euryale-v2.3-character_focus__debias.gguf \
|
20 |
+
--control-vector L3.3-70B-Euryale-v2.3-character_focus__dialogue.gguf
|
21 |
+
```
|
22 |
+
|
23 |
+
### exllamav2 with exui (via exui fork)
|
24 |
+
|
25 |
+
https://github.com/gapeleon/exui-control-vectors
|
26 |
+
|
27 |
+
1. Set it up / install it the same as regular exui
|
28 |
+
2. `pip install gguf` if you don't have it already
|
29 |
+
3. Create a directory alongside the model but with `-vectors` appended
|
30 |
+
4. Start exui `python server.py`
|
31 |
+
5. When setting up the model on the model config page, add the vectors and their scaling/direction then click "load model"
|
32 |
+
6.
|
33 |
+
Trained on 1xH100NVL using jukofyork's [control-vectors](https://github.com/jukofyork/control-vectors)
|
34 |
+
|
35 |
+
Based off Version v3.0 of [creative-writing-control-vectors-v3.0](https://huggingface.co/jukofyork/creative-writing-control-vectors-v3.0/).
|
36 |
+
|
37 |
+
See here for more info about control-vectors [creative-writing-control-vectors-v3.0](https://huggingface.co/jukofyork/creative-writing-control-vectors-v3.0/)
|