Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- not-for-all-audiences
|
| 5 |
+
- nsfw
|
| 6 |
+
---
|
| 7 |
+
## Lumimaid 0.2
|
| 8 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ep3ojmuMkFS-GmgRuI9iB.png" alt="Image" style="display: block; margin-left: auto; margin-right: auto; width: 65%;">
|
| 9 |
+
<div style="text-align: center; font-size: 30px;">
|
| 10 |
+
<a href="https://google.com">8b</a>-
|
| 11 |
+
<a href="https://google.com">12b</a>-
|
| 12 |
+
<a href="https://google.com">70b</a>-
|
| 13 |
+
<a href="https://google.com">[123b]</a>
|
| 14 |
+
</div>
|
| 15 |
+
|
| 16 |
+
### This model is based on: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
|
| 17 |
+
|
| 18 |
+
Lumimaid 0.1 -> 0.2 is a HUGE step up dataset wise.
|
| 19 |
+
As some people have told us our models are sloppy i decided to say fuck it and literally nuke all chats out with most slop.
|
| 20 |
+
On top of that Lumimaid is now mostly opus 3 sonnet, opus and a small part sonnet 3.5 based.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
## Credits:
|
| 24 |
+
- Undi
|
| 25 |
+
- IkariDev
|
| 26 |
+
|
| 27 |
+
## Training data used:
|
| 28 |
+
Will add after i can finally sleep.
|
| 29 |
+
|
| 30 |
+
## Prompt template: XXX
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
...
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
## Others
|
| 37 |
+
|
| 38 |
+
Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).
|
| 39 |
+
|
| 40 |
+
IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek
|