KaraKaraWitch
commited on
Commit
•
fd53e5a
1
Parent(s):
f330b8a
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
+
|
5 |
+
# Model Card for MythaKiCOTlion
|
6 |
+
|
7 |
+
MythaKiCOTlion is a a lora merge of Mythalion 13B + (SuperCOT + Kimiko v2)
|
8 |
+
|
9 |
+
## Model Details
|
10 |
+
|
11 |
+
*Q: **"Why do you do this?!"***
|
12 |
+
*A: **Was bored.***
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
|
17 |
+
- **Developed by:** KaraKaraWitch (Merge), kaiokendev (SuperCOT LoRA), nRuaif (Kimiko v2 LoRA)
|
18 |
+
- **Model type:** Decoder only
|
19 |
+
- **License:** LLaMA2 (MythaKiCOTlion), SuperCOT (MIT), Kimiko v1 (CC BY-NC-SA (?))
|
20 |
+
- **Finetuned from model [optional]:** LLaMA2
|
21 |
+
|
22 |
+
### Model Sources [optional]
|
23 |
+
|
24 |
+
- [Mythalion 13B](https://huggingface.co/PygmalionAI/mythalion-13b)
|
25 |
+
- [SuperCOT LoRA](https://huggingface.co/kaiokendev/SuperCOT-LoRA)
|
26 |
+
- [Kimiko v2 LoRA](https://huggingface.co/nRuaif/Kimiko-v2-13B)
|
27 |
+
|
28 |
+
|
29 |
+
## Uses
|
30 |
+
|
31 |
+
YYMV.
|
32 |
+
|
33 |
+
### Direct Use
|
34 |
+
|
35 |
+
## Usage:
|
36 |
+
|
37 |
+
Since this is a merge between Mythalion 13B, SuperCOT-LoRA and Kimiko v2, the following instruction formats should work:
|
38 |
+
|
39 |
+
Metharme:
|
40 |
+
|
41 |
+
```
|
42 |
+
<|system|>Your system prompt goes here.<|user|>Are you alive?<|model|>
|
43 |
+
```
|
44 |
+
|
45 |
+
Alpaca:
|
46 |
+
|
47 |
+
```
|
48 |
+
### Instruction:
|
49 |
+
Your instruction or question here.
|
50 |
+
### Response:
|
51 |
+
```
|
52 |
+
|
53 |
+
## Bias, Risks, and Limitations
|
54 |
+
|
55 |
+
YMMV. This is untested territory.
|
56 |
+
|
57 |
+
## Training Details
|
58 |
+
|
59 |
+
N/A. Refer to the respective LoRa's and models.
|