Merge branch 'format_1' into '0.2.5.rc1'

format readme

See merge request dcutoolkit/deeplearing/opencompass!4

README.md

@@ -123,6 +123,7 @@ python run.py configs/tgi/eval_llama2_tgi.py --debug
 HIP_VISIBLE_DEVICES=3 text-generation-launcher --dtype=float16 --model-id /data/models/Llama-2-7b-chat-hf --port 3001 --tokenizer-config-path /path/to/tokenizer_config_llama2_7b_chat.json
 ```
 注意：和base模型比多了`--tokenizer-config-path`参数。
+
 运行评测example：
 ```shell
 python run.py configs/tgi/eval_llama2_7b_chat_tgi.py.py --debug