Update README.md

README.md

@@ -39,7 +39,7 @@ otherwise the expert tensors wouldn’t be evenly sharded across GPU devices.</i
 ```
 CONTEXT_LENGTH=32768
 vllm serve \
-    tclf90/MiniMax-M2-REAP-162B-A10B-AWQ \
+    QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ \
     --served-model-name MY_MODEL \
     --enable-auto-tool-choice \
     --tool-call-parser minimax_m2 \
@@ -69,8 +69,8 @@ vllm serve \
 
 ### 【Model Download】
 ```python
-from modelscope import snapshot_download
-snapshot_download('tclf90/MiniMax-M2-REAP-162B-A10B-AWQ', cache_dir="your_local_path")
+from huggingface_hub import snapshot_download
+snapshot_download('QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ', cache_dir="your_local_path")
 ```
 
 ### 【Overview】