license: other
license_name: miqu
language:
- ko
- en
kiqu-70b
kiqu-70b is a SFT+DPO trained model based on Miqu-70B-Alpaca-DPO using Korean datasets.
Since this model is finetune of miqu-1-70b using it on commercial purposes is at your own risk. โ leaked early version Mistral-Medium
๋ณธ ๋ชจ๋ธ kiqu-70b๋ Miqu-70B-Alpaca-DPO ๋ชจ๋ธ์ ๊ธฐ๋ฐ์ผ๋ก ํ๊ตญ์ด ๋ฐ์ดํฐ์ ์ ์ฌ์ฉํ์ฌ SFT+DPO ํ๋ จ์ ์งํํ์ฌ ์ ์๋์์ต๋๋ค.
๋ฒ ์ด์ค ๋ชจ๋ธ์ธ miqu-1-70b ๋ชจ๋ธ์ด ๋ฏธ์คํธ๋-๋ฏธ๋์์ ์ด๊ธฐ ์ ์ถ ๋ฒ์ ์ด๊ธฐ์ ์์ ์ ์ฌ์ฉ์ ๋ํ risk๋ ๋ณธ์ธ์๊ฒ ์์ต๋๋ค.
Model Details
Base Model
miqu-1-70b (Early Mistral-Medium)
Instruction format
It follows Mistral format.
<s>[INST] {instruction}
[/INST] {output}</s>
Multi-shot
<s>[INST] {instruction}
[/INST] {output}
[INST] {instruction}
[/INST] {output}
[INST] {instruction}
[/INST] {output}</s>
.
.
.
Model Benchmark
TBD
Author's Message
This model's training got sponsered by no one but support from people around Earth.
Contact Me on Discord - is.maywell
Follow me on twitter - https://twitter.com/stablefluffy