Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: cc-by-nc-4.0
|
5 |
+
---
|
6 |
+
|
7 |
+
|
8 |
+
NyakuraV2 - A Multi-Turn / Instruct Mix Fine-tuned Model.
|
9 |
+
|
10 |
+
Compute is thanks to my wallet, and runpod community pod 8x a40s fior roughly 2 hours? Yeah that's it.
|
11 |
+
|
12 |
+
Trained in ShareGPT dataset format due to multi-turn capabilities.
|
13 |
+
|
14 |
+
use Vicuna 1.1 prompt format. Alpaca may work fine too, that format is like universal, may give sub-par results though..
|
15 |
+
|
16 |
+
I had much better results with the fp16 instead of GGUF, GGUF quants seem fucked? I don't know. May be on my side. Had so much nonsense input, had to wrangle settings until I had it coherent, it was working ***Really*** good. Fuck Yi models are a pain to work with.
|
17 |
+
|
18 |
+
Meow.
|
19 |
+
|
20 |
+
```
|
21 |
+
(Optional) System: <Prompt>
|
22 |
+
|
23 |
+
User: <Input>
|
24 |
+
|
25 |
+
Assistant:
|
26 |
+
```
|
27 |
+
|
28 |
+
*Example Prompt:*
|
29 |
+
|
30 |
+
```
|
31 |
+
User: Are you stand proud you're strong because you're nah I'd win, or are you nah I'd win because you're stand proud you're strong?
|
32 |
+
|
33 |
+
Assistant: You really should go to the doctor, I think you need help.
|
34 |
+
```
|
35 |
+
|
36 |
+
[Stand Proud](https://i.gyazo.com/f8f3804ca59f74372c03c8ffe3ad6f43.png)
|