timHan/llama3.2korean3B4QKM

timHan/

llama3.2korean3B4QKM:latest

4,784 Downloads Updated 8 months ago

llama-3.2-3B-Q4_K_M-Korean

tools

Updated 8 months ago

8 months ago

dfe2a261af72 · 2.0GB

archllama

parameters3.21B

quantizationQ4_K_M

2.0GB

<|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 {{ if .System }}{{

1.5kB

You are a helpful AI assistant. Please answer the user's questions kindly. 당신은 유능한 AI �

187B

{ "stop": [ "<|im_start|>", "<|im_end|>", "<|start_header_id|>",

221B

Original Model : Bllossom/llama-3.2-Korean-Bllossom-3B-gguf-Q4_K_M
Site : https://huggingface.co/Bllossom/llama-3.2-Korean-Bllossom-3B-gguf-Q4_K_M/tree/main
File : .. 2.02 GB gguf file .. download
Tool calls(Yes)

1. Download: huggingface-cli download Bllossom/llama-3.2-Korean-Bllossom-3B-gguf-Q4_K_M –local-dir /home/sguser/ollamaModels/Bllossom
2. Make Modelfile
3. Create: ollama create llama3.2korean3B4QKM -f Modelfile
4. Run : ollama run llama3.2korean3B4QKM