Update README.md

README.md

@@ -48,7 +48,9 @@ However, please note the following important conditions regarding its usage:
 
 - Install
 ```Console
-pip install -U vllm==0.7.2 sudachipy sudachidict-core
+# for CUDA 12.1
+pip install torch==2.5.1 --index-url https://download.pytorch.org/whl/cu121
+pip install vllm==0.7.2 sudachipy sudachidict-core
 ```
 
 In this first release, we only provide code example using the [sudachipy](https://github.com/WorksApplications/SudachiPy) tokenizer, which matches the token boundaries of UD Japanese datasets.
@@ -143,7 +145,7 @@ for sentence, result in zip(input_sentences, results):
     print(result.outputs[0].text)
 ```
 
-- Output of code example
+- Outputs of Code example
 ```
 # text = 銀座でランチをご一緒しましょう。
 - Task 1
@@ -288,8 +290,8 @@ The details of the experimental conditions will be released later.
 
 ### Evaluation Results
 
-The accuracies in the table below are based on the simple recovery process applied to the TSV output in Step 3.  
-次の表に記載した精度は、Step 3のTSV出力に簡易なリカバリ処理を適用した上で評価を行っています。
+The accuracies in the table below are based on the simple recovery process applied to the TSV output in Step 3, by using the gold tokens from the test set of the UD dataset for the seven languages ​​mentioned above.  
+次の表に記載した精度は、前述の7言語のUDデータセットのtestセットの正解トークンを用いて、Step 3のTSV出力に簡易なリカバリ処理を適用した上で評価を行っています。
 | dataset | UPOS | UAS | LAS |
 | ---- | ---- | ---- | ---- |
 | [UD_English-EWT](https://github.com/UniversalDependencies/UD_English-EWT) | 0.982 | 0.951 | 0.937 |