Model Card for PygKiCOTlion
PygKiCOTlion is a a lora merge of Pygmalion-2-13b-SuperCOT + Kimiko v2
Model Details
Q: "Why do you do this?!"
A: Was bored.
Model Description
- Developed by: KaraKaraWitch (Merge), kaiokendev (Original SuperCOT LoRA), nRuaif (Kimiko v2 LoRA), kingbri (Pygmalion 2 13b SuperCOT)
- Model type: Decoder only
- License: LLaMA2 (PygKiCOTlion), SuperCOT (MIT), Kimiko v2 (CC BY-NC-SA (?))
- Finetuned from model [optional]: LLaMA2
Model Sources [optional]
Uses
YYMV.
Direct Use
Usage:
Since this is a merge between Pygmalion 2 13b SuperCOT 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
Notes from KaraKaraWitch:
- The model feels weirdly loopy compared to MythKiCOTlion at lower temps.
- Higher temps the model tries to venture out of it's comfort zone at the cost of making it not stick to the model card as close as expected.
Training Details
N/A. Refer to the respective LoRa's and models.