Update README.md

README.md

@@ -75,12 +75,12 @@ GitHub: https://github.com/ku-nlp/ja-vicuna-qa-benchmark
 
 | model | time [s] for genrating 100 characters in Japanese |
 |:---:|:---:|
-|stockmark-100b-instruct[^2]| 1.86 |
+|stockmark-100b-instruct| 1.86 |
 | gpt-3.5-turbo | 2.15 |
 | gpt-4-turbo | 5.48 |
-|tokyotech-llm/Swallow-70b-instruct-hf[^2]| 2.22 |
+|tokyotech-llm/Swallow-70b-instruct-hf| 2.22 |
 
-[^2]: We measured the time using AWS Inferentia2.
+For local LLMs, we measured the inference time using AWS Inferentia2.
 
 ## License
 [MIT](https://opensource.org/licenses/MIT)