Fix benchmark note: remove inaccurate FP8 baseline line, correct max tokens to 384000

README.md

@@ -166,8 +166,7 @@ The accuracy benchmark results are presented in the table below:
   </tr>
 </table>
 
-> Baseline (ours): our measurement of [DeepSeek-V4-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash) in its native FP8 format.
-> Benchmarked with temperature=1.0, top_p=1.0, max num tokens 64000
+> Benchmarked with temperature=1.0, top_p=1.0, max num tokens 384000
 
  Model Limitations:
 The base model was trained on data that contains toxic language and societal biases originally crawled from the internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts. The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.