Update README.md

README.md

@@ -110,7 +110,6 @@ The results of AIME24, MATH-500, and GPQA Diamond, were obtained using forked [l
 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"
 
@@ -118,6 +117,7 @@ LOG="logs/deepseek_0528_maxfp4.log"
 for i in $(seq 1 10); do
     # seed in [0, 2**30 - 1]
     SEED=$(shuf -i 0-1073741823 -n 1)
+    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}"
 
     lighteval vllm $MODEL_ARGS "custom|aime24_single|0|0,custom|math_500_single|0|0,custom|gpqa:diamond_single|0|0" \
         --use-chat-template \