Update README.md

README.md

@@ -38,7 +38,7 @@ export VLLM_USE_FLASHINFER_SAMPLER=0
 export OMP_NUM_THREADS=4
 
 vllm serve \
-    __YOUR_PATH__/tclf90/GLM-4.7-GPTQ-Int4-Int8Mix \
+    __YOUR_PATH__/QuantTrio/GLM-4.7-GPTQ-Int4-Int8Mix \
     --served-model-name MY_MODEL_NAME \
     --swap-space 16 \
     --max-num-seqs 32 \
@@ -69,8 +69,8 @@ vllm serve \
 
 ### 【Model Download】
 ```python
-from modelscope import snapshot_download
-snapshot_download('tclf90/GLM-4.7-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")
+from huggingface_hub  import snapshot_download
+snapshot_download('QuantTrio/GLM-4.7-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")
 ```
 
 ### 【Overview】