try fix

.gitignore

@@ -1,3 +1,4 @@
 # Sphinx documentation
 docs/_build/
-docs/build/
+docs/build/
+docs/**/*.mo

docs/locales/zh_CN/LC_MESSAGES/benchmark/quantization_benchmark.po

@@ -3,12 +3,11 @@
 # This file is distributed under the same license as the Qwen package.
 # FIRST AUTHOR <EMAIL@ADDRESS>, 2024.
 #
-
 msgid ""
 msgstr ""
 "Project-Id-Version: Qwen \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-06-06 22:57+0800\n"
+"POT-Creation-Date: 2024-06-07 00:12+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -29,8 +28,7 @@ msgstr "量化模型效果评估"
 msgid ""
 "This section reports the generation performance of quantized models "
 "(including GPTQ and AWQ) of the Qwen2 series. Specifically, we report:"
-msgstr ""
-"本部分介绍Qwen2量化模型（包括GPTQ与AWQ量化方案）的效果评估，有以下数据集"
+msgstr "本部分介绍Qwen2量化模型（包括GPTQ与AWQ量化方案）的效果评估，有以下数据集"
 
 #: ../../source/benchmark/quantization_benchmark.rst:8
 #: 504942421d70442cbcc85f254f9a5393
@@ -79,7 +77,7 @@ msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:17
 #: f0f1619f24c04c51bdb22ec7372519a6
-msgid "Qwen-72B-Instruct"
+msgid "Qwen2-72B-Instruct"
 msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:17
@@ -192,7 +190,7 @@ msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:25
 #: 1de269e970524699b7d15bee6cdc4cf2
-msgid "Qwen-7B-Instruct"
+msgid "Qwen2-7B-Instruct"
 msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:25
@@ -273,7 +271,7 @@ msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:33
 #: 533c3883c1874874a7c787d288ea9d3e
-msgid "Qwen-1.5B-Instruct"
+msgid "Qwen2-1.5B-Instruct"
 msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:33
@@ -358,7 +356,7 @@ msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:41
 #: ad428acda07643d0bb1274ce8e8c2c75
-msgid "Qwen-0.5B-Instruct"
+msgid "Qwen2-0.5B-Instruct"
 msgstr ""
 
 #: ../../source/benchmark/quantization_benchmark.rst:41

docs/locales/zh_CN/LC_MESSAGES/benchmark/speed_benchmark.po

@@ -37,7 +37,7 @@ msgstr ""
 #: ../../source/benchmark/speed_benchmark.rst:9
 #: 7b78fe22b047416695692b0885ca369d
 msgid "The environment of the evaluation with huggingface transformers is:"
-msgstr "测试HuggingFace ``transformers``时的环境配置："
+msgstr "测试HuggingFace ``transformers`` 时的环境配置："
 
 #: ../../source/benchmark/speed_benchmark.rst:11
 #: ../../source/benchmark/speed_benchmark.rst:21

docs/locales/zh_CN/LC_MESSAGES/run_locally/mlx-lm.po

@@ -31,7 +31,7 @@ msgid ""
 "checkpoints that you can directly use with it."
 msgstr ""
 "`mlx-lm <https://github.com/ml-explore/mlx-examples/tree/main/llms>`__ "
-"能让你在Apple Silicon上运行大型语言模型，适用于MacOS。``mlx-lm``已支持Qwen模型，"
+"能让你在Apple Silicon上运行大型语言模型，适用于MacOS。``mlx-lm`` 已支持Qwen模型，"
 "此次我们提供直接可用的模型文件。"
 
 #: ../../source/run_locally/mlx-lm.rst:9 41cb684fde614a7b964fd9e470ea972b