Update instruction in Readme

README.md

@@ -45,6 +45,8 @@ vllm serve \
 ### Evaluation
 From vllm-bench, the acceptance length (AL) on HumanEval dataset with different speculation length K is shown as below.
 
+We use instruction-formatted prompts following standard practice for instruct models (similar to [DeepSeek-Coder evaluation](https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/Evaluation/HumanEval/eval_instruct.py) and [Llama 3.1 8B instruction evaluation](https://huggingface.co/datasets/meta-llama/Llama-3.1-8B-Instruct-evals/viewer/Llama-3.1-8B-Instruct-evals__human_eval__details?row=1)). The instruction we add in front of each prompt is ```Complete the following Python function. Only output the code, no explanations.```
+
   | K | Acceptance Length |
   |---|-------------------|
   | 4 | 4.30 |
@@ -60,7 +62,7 @@ vllm bench serve \
       --model Qwen/Qwen3-Coder-30B-A3B-Instruct \
       --dataset-name custom \
       --dataset-path /home/ubuntu/eval_datasets/humaneval_qwen3coder_bench.jsonl \
-      --custom-output-len 4096 \
+      --custom-output-len 256 \
       --num-prompts 80 \
       --max-concurrency 1 \
       --temperature 0 \