Update README.md

README.md

@@ -51,7 +51,7 @@ This model can be deployed efficiently using the [SGLang](https://docs.sglang.ai
 
 ## Evaluation
 
-The model was evaluated on AIME24, GPQA Diamond, MATH-500, and GSM8K benchmarks. The tasks of AIME24, GPQA Diamond, and MATH-500 were conducted using the [lighteval](https://github.com/huggingface/lighteval/tree/v0.10.0) framework while GSM8K using [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness).
+The model was evaluated on AIME24, GPQA Diamond, MATH-500, and GSM8K benchmarks. The tasks of AIME24, GPQA Diamond, and MATH-500 were conducted using [lighteval](https://github.com/huggingface/lighteval/tree/v0.10.0) with 10 rounds for different generation seeds. GSM8K was conducted using [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness).
 
 ### Accuracy
 
@@ -111,8 +111,7 @@ The model was evaluated on AIME24, GPQA Diamond, MATH-500, and GSM8K benchmarks.
 
 ### Reproduction
 
-The results can be reproduced using vLLM emulation docker: `rocmshared/pytorch:vllm-gfx950-mxfp4-mxfp6-v3`.
-The results of AIME24, MATH-500, and GPQA Diamond, were obtained using [vLLM](https://docs.vllm.ai/en/latest/) while GSM8K was obtained using [SGLang](https://docs.sglang.ai/). For AIME24, MATH-500, and GPQA Diamond, we took 10 rounds with different random seeds for reliable performance.
+The results of AIME24, MATH-500, and GPQA Diamond, were obtained using [lighteval](https://github.com/huggingface/lighteval/tree/v0.10.0) and [vLLM](https://docs.vllm.ai/en/latest/), running with docker `rocm/vllm-private:pytorch-vllm-gfx950-mxfp4-mxfp6-v3`.
 
 ```
 MODEL_ARGS="model_name=amd/DeepSeek-R1-0528-MXFP4-ASQ,dtype=bfloat16,tensor_parallel_size=8,max_model_length=71536,max_num_batched_tokens=32768,gpu_memory_utilization=0.85,generation_parameters={max_new_tokens:65536,temperature:0.6,top_p:0.95,seed:$SEED}"