Update README.md

README.md

@@ -11,7 +11,7 @@ base_model:
 base_model_relation: quantized
 ---
 # Kimi-K2.5-E304
-Base model: [moonshotai/Kimi-K2.5](https://www.modelscope.cn/models/moonshotai/Kimi-K2.5)
+Base model: [moonshotai/Kimi-K2.5](https://huggingface.co/moonshotai/Kimi-K2.5)
 
 This repo trims 20% of the experts (384 → 304); 
 
@@ -30,8 +30,8 @@ The model format and serving setup (vLLM/SGLang versions and launch commands) ma
 
 ### 【Model Download】
 ```python
-from modelscope import snapshot_download
-snapshot_download('tclf90/Kimi-K2.5-E304', cache_dir="your_local_path")
+from huggingface_hub import snapshot_download
+snapshot_download('QuantTrio/Kimi-K2.5-E304', cache_dir="your_local_path")
 ```
 
 ### 【Overview】