Update README.md

README.md

@@ -113,7 +113,7 @@ lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks
 
 ## float8dq
 ```
-lm_eval --model hf --model_args pretrained=jerryzh168/phi4-mini-float8dq --tasks hellaswag --device cuda:0 --batch_size 8
+lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-float8dq --tasks hellaswag --device cuda:0 --batch_size 8
 ```
 
 `TODO: more complete eval results`
@@ -163,7 +163,7 @@ python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model
 
 ### float8dq
 ```
-python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model jerryzh168/phi4-mini-float8dq --batch-size 1
+python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model pytorch/Phi-4-mini-instruct-float8dq --batch-size 1
 ```
 
 ## benchmark_serving
@@ -186,7 +186,7 @@ python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --
 ### float8dq
 Server:
 ```
-vllm serve jerryzh168/phi4-mini-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3
+vllm serve pytorch/Phi-4-mini-instruct-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3
 ```
 
 Client:
@@ -197,5 +197,5 @@ python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --
 # Serving with vllm
 We can use the same command we used in serving benchmarks to serve the model with vllm
 ```
-vllm serve jerryzh168/phi4-mini-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3
+vllm serve pytorch/Phi-4-mini-instruct-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3
 ```