Update README.md

README.md

@@ -130,7 +130,7 @@ The model was evaluated on the OpenLLM leaderboard tasks (versions 1 and 2), usi
   ```
   lm_eval \
     --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-4B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \
+    --model_args pretrained="RedHatAI/Qwen3-8B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks openllm \
     --apply_chat_template\
     --fewshot_as_multiturn \
@@ -140,7 +140,7 @@ The model was evaluated on the OpenLLM leaderboard tasks (versions 1 and 2), usi
   ```
   lm_eval \
     --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-4B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \
+    --model_args pretrained="RedHatAI/Qwen3-8B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks mgsm \
     --apply_chat_template\
     --batch_size auto
@@ -149,7 +149,7 @@ The model was evaluated on the OpenLLM leaderboard tasks (versions 1 and 2), usi
   ```
   lm_eval \
     --model vllm \
-    --model_args pretrained="RedHatAI/Qwen3-4B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=16384,enable_chunk_prefill=True,tensor_parallel_size=1 \
+    --model_args pretrained="RedHatAI/Qwen3-8B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.5,max_model_len=16384,enable_chunk_prefill=True,tensor_parallel_size=1 \
     --tasks leaderboard \
     --apply_chat_template\
     --fewshot_as_multiturn \
@@ -161,7 +161,7 @@ The model was evaluated on the OpenLLM leaderboard tasks (versions 1 and 2), usi
   lighteval_model_arguments.yaml
   ```yaml 
   model_parameters:
-    model_name: RedHatAI/Qwen3-4B-FP8-dynamic
+    model_name: RedHatAI/Qwen3-8B-FP8-dynamic
     dtype: auto
     gpu_memory_utilization: 0.9
     max_model_length: 40960