KaraKaraWitch's picture
Update README.md
64a5626
---
{}
---
# Model Card for MythaKiCOTlion
MythaKiCOTlion is a a lora merge of Mythalion 13B + (SuperCOT + Kimiko v2)
## Model Details
*Q: **"Why do you do this?!"***
*A: **Was bored.***
### Model Description
- **Developed by:** KaraKaraWitch (Merge), kaiokendev (SuperCOT LoRA), nRuaif (Kimiko v2 LoRA)
- **Model type:** Decoder only
- **License:** LLaMA2 (MythaKiCOTlion), SuperCOT (MIT), Kimiko v1 (CC BY-NC-SA (?))
- **Finetuned from model [optional]:** LLaMA2
### Model Sources [optional]
- [Mythalion 13B](https://huggingface.co/PygmalionAI/mythalion-13b)
- [SuperCOT LoRA](https://huggingface.co/kaiokendev/SuperCOT-LoRA)
- [Kimiko v2 LoRA](https://huggingface.co/nRuaif/Kimiko-v2-13B)
## Uses
YYMV.
### Direct Use
## Usage:
Since this is a merge between Mythalion 13B, SuperCOT-LoRA and Kimiko v2, the following instruction formats should work:
Metharme:
```
<|system|>Your system prompt goes here.<|user|>Are you alive?<|model|>
```
Alpaca:
```
### Instruction:
Your instruction or question here.
### Response:
```
## Bias, Risks, and Limitations
YMMV. This is untested territory.
### Testing Feedbakc
- The model appears to still suffers from Mythalion annoyances.
- *Which is to be expected, I'm thinking SuperCOT + Pyg2 Might be the way to go. Guess that's gonna be my next step.*
Thanks to Trappu for the preliminary Feedback!
## Training Details
N/A. Refer to the respective LoRa's and models.