Update README.md

README.md

@@ -47,7 +47,7 @@ This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/
 from vllm import LLM, SamplingParams
 from transformers import AutoTokenizer
 
-model_id = "neuralmagic/Qwen2.5-72B-quantized.w8a8"
+model_id = "neuralmagic-ent/Qwen2.5-72B-quantized.w8a8"
 number_gpus = 2
 max_model_len = 8192
 
@@ -74,7 +74,7 @@ The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-
 ```
 lm_eval \
   --model vllm \
-  --model_args pretrained="neuralmagic/Qwen2.5-72B-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=2 \
+  --model_args pretrained="neuralmagic-ent/Qwen2.5-72B-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=2 \
   --tasks openllm \
   --batch_size auto
 ```