Update README.md

README.md

@@ -100,13 +100,18 @@ The model was evaluated on AIME24, GPQA Diamond, and MATH-500 benchmarks using t
 
 ### Reproduction
 
-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`.
+The results of AIME24, MATH-500, and GPQA Diamond, were obtained using forked [lighteval](https://github.com/zhaolin-amd/lighteval/tree/v0.10-release-custom) and vLLM docker `rocm/vllm-private:pytorch-vllm-gfx950-mxfp4-mxfp6-v3`.
 
 ```
+# Set docker env
+export VLLM_QUARK_F4F6_OFFLINE_DEQUANT_TMPENVVAR=1
+
+# Set model args
 MODEL_ARGS="model_name=amd/DeepSeek-R1-0528-MXFP4-Preview,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}"
 OUTPUT_DIR="results/DeepSeek-R1-0528-MXFP4-Preview-Seed"
 LOG="logs/deepseek_0528_maxfp4.log"
 
+# Evaluating 10 rounds 
 for i in $(seq 1 10); do
     # seed in [0, 2**30 - 1]
     SEED=$(shuf -i 0-1073741823 -n 1)