Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: kakaocorp/kanana-safeguard-siren-8b
+base_model: kakaocorp/kanana-safeguard-8b
 quantized_by: Arc1el
 quantization_method: bitsandbytes
 model_type: llama
@@ -17,7 +17,7 @@ pipeline_tag: text-generation
 # Kanana Safeguard Siren 8B - 4bit 양자화 버전
 
 ## 모델 개요
-- **원본 모델**: [kakaocorp/kanana-safeguard-siren-8b](https://huggingface.co/kakaocorp/kanana-safeguard-siren-8b)
+- **원본 모델**: [kakaocorp/kanana-safeguard-8b](https://huggingface.co/kakaocorp/kanana-safeguard-8b)
 - **양자화 방법**: BitsAndBytes 4bit (NF4)
 - **양자화 도구**: bitsandbytes + transformers
 - **압축률**: 원본 대비 약 75% 크기 감소 (추정)
@@ -59,7 +59,7 @@ pip install transformers accelerate bitsandbytes torch
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
-model_name = "[your-username]/kanana-safeguard-siren-8b-4bit"
+model_name = "nxtcloud-org/kanana-safeguard-siren-8b-4bit"
 
 # BitsAndBytesConfig 설정
 bnb_config = BitsAndBytesConfig(
@@ -130,7 +130,6 @@ print(result)
 
 ```
 Copyright 2025 Kakao Corp. (Original model)
-Copyright 2025 [Your Name] (Quantization)
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
@@ -154,6 +153,6 @@ limitations under the License.
   author={Kakao Corp},
   year={2024},
   publisher={Hugging Face},
-  url={https://huggingface.co/kakaocorp/kanana-safeguard-siren-8b}
+  url={https://huggingface.co/kakaocorp/kanana-safeguard-8b}
 }
 ```