fix typos

README.md

@@ -39,7 +39,7 @@ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 generated_ids = model.generate(
     **model_inputs,
     max_new_tokens=512,
-    do_sample=False
+    do_sample=False ##change this to follow official usage
 )
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
@@ -192,7 +192,7 @@ I think the answer is three.
 pip3 install lm-eval==0.4.5
 
 ```bash
-auto-round --model "Intel/OPEA/QwQ-32B-Preview-int4-sym-mixed-inc" --eval --eval_bs 16  --tasks leaderboard_ifeval,leaderboard_mmlu_pro,gsm8k,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,cmmlu,ceval-valid
+auto-round --model "OPEA/QwQ-32B-Preview-int4-sym-mixed-inc" --eval --eval_bs 16  --tasks leaderboard_ifeval,leaderboard_mmlu_pro,gsm8k,lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,cmmlu,ceval-valid
 ```
 
 | Metric                                   |           BF16           |           INT4           | iter1000 nsamples 512    |