Skip to content

Latest commit

 

History

History
 
 

Llama-3-Open-Ko-8B

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 

Llama-3-Open-Ko 공개(2024.04.24)

STEP 1. gguf 모델 다운로드

STEP 2. Modelfile

FROM Meta-Llama-3-8B-Instruct.Q8_0.gguf

TEMPLATE """{{- if .System }}
<|begin_of_text|>system {{ .System }}<|end_of_text|>
{{- end }}
<|begin_of_text|>user
{{ .Prompt }}<|end_of_text|>
<|begin_of_text|>assistant
"""

SYSTEM """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."""

PARAMETER temperature 0
PARAMETER num_ctx 4096
PARAMETER stop <|begin_of_text|>
PARAMETER stop <|end_of_text|>
PARAMETER stop <|eot_id|>
PARAMETER stop <|end_of_text|>

STEP 3. Ollama 모델 생성

ollama create llama3-instruct-8b -f Modelfile

STEP 4. 잘 만들어 졌는지 확인

ollama list

출력되는 결과에 내가 만든 모델이 뜨는지 확인해 주세요.

STEP 5. Ollama 실행

ollama run llama3-instruct-8b