Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
tags:
|
4 |
+
- not-for-all-audiences
|
5 |
+
- nsfw
|
6 |
+
---
|
7 |
+
|
8 |
+
Merge of OpenHermes and Dolphin with 2x Noromaid DPO, trying to add a little more brain in the model, while being smaller than a 8x7b.
|
9 |
+
|
10 |
+
It seems to work well.
|
11 |
+
|
12 |
+
<!-- description start -->
|
13 |
+
## Description
|
14 |
+
|
15 |
+
This repo contains GGUF files of OpenDolphinMaid-4x7b.
|
16 |
+
|
17 |
+
<!-- description end -->
|
18 |
+
<!-- description start -->
|
19 |
+
## Models and LoRA used
|
20 |
+
|
21 |
+
- NeverSleep/Noromaid-7B-0.4-DPO x 2
|
22 |
+
- teknium/OpenHermes-2.5-Mistral-7B
|
23 |
+
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo
|
24 |
+
|
25 |
+
<!-- description end -->
|
26 |
+
<!-- prompt-template start -->
|
27 |
+
## Prompt template: Chatml
|
28 |
+
|
29 |
+
```
|
30 |
+
<|im_start|>system
|
31 |
+
{sysprompt}<|im_end|>
|
32 |
+
<|im_start|>user
|
33 |
+
{prompt}<|im_end|>
|
34 |
+
<|im_start|>assistant
|
35 |
+
```
|
36 |
+
|
37 |
+
If you want to support me, you can [here](https://ko-fi.com/undiai).
|