HelloGitHub commited on
Commit
73f1b9b
·
1 Parent(s): e854023

fix table bug

Browse files
Files changed (2) hide show
  1. app.py +4 -1
  2. src/about.py +4 -0
app.py CHANGED
@@ -10,6 +10,8 @@ from src.about import (
10
  EVALUATION_QUEUE_TEXT,
11
  INTRODUCTION_TEXT,
12
  LLM_BENCHMARKS_TEXT,
 
 
13
  TITLE,
14
  EVALUATION_METRIC_TEXT,
15
  )
@@ -429,7 +431,8 @@ with demo:
429
  gr.Markdown(EVALUATION_METRIC_TEXT, elem_classes="markdown-text")
430
  with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
431
  gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
432
-
 
433
 
434
  with gr.Row():
435
  with gr.Accordion("📙 Citation", open=False):
 
10
  EVALUATION_QUEUE_TEXT,
11
  INTRODUCTION_TEXT,
12
  LLM_BENCHMARKS_TEXT,
13
+ LLM_BENCHMARKS_TEXT2,
14
+ TABLE_TEXT,
15
  TITLE,
16
  EVALUATION_METRIC_TEXT,
17
  )
 
431
  gr.Markdown(EVALUATION_METRIC_TEXT, elem_classes="markdown-text")
432
  with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
433
  gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
434
+ gr.HTML(TABLE_TEXT)
435
+ gr.Markdown(LLM_BENCHMARKS_TEXT2, elem_classes="markdown-text")
436
 
437
  with gr.Row():
438
  with gr.Accordion("📙 Citation", open=False):
src/about.py CHANGED
@@ -176,7 +176,9 @@ Planning
176
  我们对上述10个数据集的数据进行了能力维度划分,归纳出具身智能场景需要的4大能力维度空间理解,感知,预测,规划。并按照能力维度,采样出一个样本数为2042的优质子集,能力维度定义和各维度的数据量如下:
177
 
178
  We have categorized the data of the above 10 datasets by capability dimensions, and summarized four major capability dimensions required for embodied intelligence scenarios: spatial reasoning, perception, prediction, and planning. According to the capability dimensions, a high-quality subset with 2,042 samples was sampled. The definitions of the capability dimensions and the data volume of each dimension are as follows:
 
179
 
 
180
  <table>
181
  <thead>
182
  <tr>
@@ -263,7 +265,9 @@ We have categorized the data of the above 10 datasets by capability dimensions,
263
  </tr>
264
  </tbody>
265
  </table>
 
266
 
 
267
  ## EmbodiedVerse Tool - FlagEvalMM
268
 
269
  FlagEvalMM是一个开源评估框架,旨在全面评估多模态模型,其提供了一种标准化的方法来评估跨各种任务和指标使用多种模式(文本、图像、视频)的模型。
 
176
  我们对上述10个数据集的数据进行了能力维度划分,归纳出具身智能场景需要的4大能力维度空间理解,感知,预测,规划。并按照能力维度,采样出一个样本数为2042的优质子集,能力维度定义和各维度的数据量如下:
177
 
178
  We have categorized the data of the above 10 datasets by capability dimensions, and summarized four major capability dimensions required for embodied intelligence scenarios: spatial reasoning, perception, prediction, and planning. According to the capability dimensions, a high-quality subset with 2,042 samples was sampled. The definitions of the capability dimensions and the data volume of each dimension are as follows:
179
+ """
180
 
181
+ TABLE_TEXT = """
182
  <table>
183
  <thead>
184
  <tr>
 
265
  </tr>
266
  </tbody>
267
  </table>
268
+ """
269
 
270
+ LLM_BENCHMARKS_TEXT2 = """
271
  ## EmbodiedVerse Tool - FlagEvalMM
272
 
273
  FlagEvalMM是一个开源评估框架,旨在全面评估多模态模型,其提供了一种标准化的方法来评估跨各种任务和指标使用多种模式(文本、图像、视频)的模型。