Update README.md

README.md

@@ -36,7 +36,6 @@ cd Quark/examples/torch/language_modeling/llm_ptq/
 exclude_layers="*self_attn* *mlp.gate.* *lm_head"
 python3 quantize_quark.py --model_dir $MODEL_DIR \
                           --quant_scheme w_mxfp4_a_mxfp4 \
-                          --group_size 32 \
                           --num_calib_data 128 \
                           --exclude_layers $exclude_layers \
                           --multi_gpu \
@@ -52,7 +51,8 @@ This model can be deployed efficiently using the [SGLang](https://docs.sglang.ai
 
 ## Evaluation
 
-The model was evaluated on AIME24, GPQA Diamond, and MATH-500 benchmarks using the [lighteval](https://github.com/huggingface/lighteval/tree/v0.10.0) framework. Each benchmark was run 10 times with different random seeds for reliable performance estimation.
+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, with each tasks running 10 times using different random seeds for reliable performance estimation.
+The task of GSM8K was conducted 
 
 ### Accuracy
 
@@ -98,7 +98,7 @@ The model was evaluated on AIME24, GPQA Diamond, and MATH-500 benchmarks using t
    </td>
   </tr>
   <tr>
-   <td>gsm8k 
+   <td>GSM8K 
    </td>
    <td>95.30
    </td>
@@ -125,7 +125,7 @@ lighteval vllm $MODEL_ARGS "custom|aime24_single|0|0,custom|math_500_single|0|0,
     2>&1 | tee -a "$LOG"
 ```
 
-The result of gsm8k was obtained using lm-eval-harness.
+The result of gsm8k was obtained using [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness).
 
 ```
 MODEL_ARGS="model=amd/DeepSeek-R1-0528-MXFP4-ASQ,base_url=http://localhost:8000/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=38768,temperature=0.6,top_p=0.95,add_bos_token=True,seed=$SEED"