jinbora/
deepseek-r1-Bllossom:70b-q8_0

1,198 7 months ago

A Korean fine-tuned version of deepseek-r1 by UNIVA and the Bllossom team.

8b 70b

7 months ago

736899165c08 · 75GB

model
llama
·
70.6B
·
Q8_0
license
MIT License Copyright (c) 2023 DeepSeek Permission is hereby granted, free of charge, to any person
params
{ "stop": [ "<|begin▁of▁sentence|>", "<|end▁of▁sentence|>", "<|U
template
{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice

Readme

This model is a fine-tuned for Koreanl developed by UNIVA and the Bllossom team.
This is a model where most instances of Chinese mixing into Korean responses have been resolved.
You can find the original model on Hugging Face at the following link:

* DeepSeek-llama3.3-Bllossom-70B
* DeepSeek-llama3.1-Bllossom-8B

이 모델은 UNIVA와 Bllossom 팀이 개발한 한국어용으로 미세 조정된 모델입니다.
한글로 응답을 하는 경우 중국어가 섞여나오는 부분이 대부분 해소된 모델입니다.
다음 링크에서 Hugging Face의 원래 모델을 찾을 수 있습니다.

* DeepSeek-llama3.3-Bllossom-70B
* DeepSeek-llama3.1-Bllossom-8B