Update README.md

README.md

@@ -4,19 +4,19 @@ language:
   - zh
 library_name: transformers
 license: mit
+pipeline_tag: text-generation
 tasks:
   - text-generation
 frameworks: PyTorch
-pipeline_tag: text-to-text
 tags:
 - vLLM
 - AWQ
 base_model:
-  - ZhipuAI/GLM-4.7-Flash
+  - zai-org/GLM-4.7-Flash
 base_model_relation: quantized
 ---
 # GLM-4.7-Flash-AWQ
-Base model: [ZhipuAI/GLM-4.7-Flash](https://www.modelscope.cn/models/ZhipuAI/GLM-4.7-Flash)
+Base model: [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash)
 
 
 ### 【Dependencies / Installation】
@@ -42,7 +42,7 @@ export VLLM_USE_FLASHINFER_SAMPLER=0
 export OMP_NUM_THREADS=4
 
 vllm serve \
-    __YOUR_PATH__/tclf90/GLM-4.7-Flash-AWQ \
+    __YOUR_PATH__/QuantTrio/GLM-4.7-Flash-AWQ \
     --served-model-name MY_MODEL_NAME \
     --swap-space 4 \
     --max-model-len 32768 \
@@ -72,8 +72,8 @@ vllm serve \
 
 ### 【Model Download】
 ```python
-from modelscope import snapshot_download
-snapshot_download('tclf90/GLM-4.7-Flash-AWQ', cache_dir="your_local_path")
+from huggingface_hub import snapshot_download
+snapshot_download('QuantTrio/GLM-4.7-Flash-AWQ', cache_dir="your_local_path")
 ```
 
 ### 【Overview】