Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- ewof/koishi-instruct-metharme
|
4 |
+
- PygmalionAI/PIPPA
|
5 |
+
---
|
6 |
+
|
7 |
+
## Base Model
|
8 |
+
|
9 |
+
native fine tune of ludis/tsukasa-7b
|
10 |
+
|
11 |
+
## Prompting
|
12 |
+
|
13 |
+
The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
|
14 |
+
|
15 |
+
The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
|
16 |
+
|
17 |
+
## Benchmarks
|
18 |
+
|
19 |
+
trained on commit de693ac of the koishi dataset
|
20 |
+
|
21 |
+
trained on commit 36fc235 of pippa metharme
|
22 |
+
|
23 |
+
trained on Version 2023-09-03 of LimaRP (without ponyville, lolicit, all the fallen, and eka's portal subsets)
|
24 |
+
|
25 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f38f3a89203d118da8b477/lvXgfxrb5v4ceEtZfVrYP.png)
|