timHan/llama3korean8B4QKM

timHan/

llama3korean8B4QKM:latest

1,041 Downloads Updated 8 months ago

llama-3-Korean-Bllossom-8B-Q4_K_M

Updated 8 months ago

8 months ago

20247f89c0bc · 4.9GB

archllama

·

parameters8.03B

·

quantizationQ4_K_M

4.9GB

당신은 유용한 AI 어시스턴트입니다. 사용자의 질의에 대해 친절하고 정확�

233B

{ "stop": [ "<|im_start|>", "<|im_end|>" ], "temperature": 0, "top_p

87B

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

161B

Readme

Information

Original Model : MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M
Site : https://huggingface.co/MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M/tree/main
File : .. 4.92 GB gguf file .. download
Tool calls(No)

Process

1. Download: huggingface-cli download MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M –local-dir /home/sguser/ollamaModels/MLP-KTLim
2. Make Modelfile
3. Create: ollama create llama3korean8B4QKM -f Modelfile
4. Run : ollama run llama3korean8B4QKM