Terry Zhuo commited on
Commit
5874e3d
·
1 Parent(s): 14a3287
Files changed (2) hide show
  1. src/display/about.py +1 -1
  2. src/display/utils.py +2 -2
src/display/about.py CHANGED
@@ -1,4 +1,4 @@
1
- TITLE = """<div style="text-align: center;"><h1> 🌸<span style='color: #C867B5;'>BigCodeBench</span> Leaderboard</h1></div>\
2
  <br>\
3
  <p>Inspired from the <a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">🤗 Open LLM Leaderboard</a> and <a href="https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard">⭐ Big Code Models Leaderboard</a>, we compare performance of LLMs on <a href="https://huggingface.co/datasets/bigcode/bigcodebench">BigCodeBench</a> benchmark.</p>
4
  <p>To get started, please check out <a href="https://github.com/bigcode-project/bigcodebench">our GitHub repository</a>.
 
1
+ TITLE = """<div style="text-align: center;"><h1> 🌸<span style='color: #C867B5;'>BigCodeBench-Hard</span> Leaderboard</h1></div>\
2
  <br>\
3
  <p>Inspired from the <a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">🤗 Open LLM Leaderboard</a> and <a href="https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard">⭐ Big Code Models Leaderboard</a>, we compare performance of LLMs on <a href="https://huggingface.co/datasets/bigcode/bigcodebench">BigCodeBench</a> benchmark.</p>
4
  <p>To get started, please check out <a href="https://github.com/bigcode-project/bigcodebench">our GitHub repository</a>.
src/display/utils.py CHANGED
@@ -59,7 +59,7 @@ column_map = {
59
  "act_param": "#Act Params (B)",
60
  "size": "#Params (B)",
61
  "moe": "MoE",
62
- "lazy": "Lazy",
63
  "openness": "Openness",
64
  # "direct_complete": "Direct Completion",
65
  }
@@ -102,7 +102,7 @@ auto_eval_column_dict.append(["elo_mle", ColumnContent, ColumnContent(column_map
102
  auto_eval_column_dict.append(["act_param", ColumnContent, ColumnContent(column_map["act_param"], "number", True)])
103
  auto_eval_column_dict.append(["link", ColumnContent, ColumnContent(column_map["link"], "str", False, True)])
104
  auto_eval_column_dict.append(["size", ColumnContent, ColumnContent(column_map["size"], "number", False)])
105
- auto_eval_column_dict.append(["lazy", ColumnContent, ColumnContent(column_map["lazy"], "bool", False, True)])
106
  auto_eval_column_dict.append(["moe", ColumnContent, ColumnContent(column_map["moe"], "str", False, True)])
107
  auto_eval_column_dict.append(["openness", ColumnContent, ColumnContent(column_map["openness"], "str", False, True)])
108
  # auto_eval_column_dict.append(["direct_complete", ColumnContent, ColumnContent(column_map["direct_complete"], "bool", False)])
 
59
  "act_param": "#Act Params (B)",
60
  "size": "#Params (B)",
61
  "moe": "MoE",
62
+ # "lazy": "Lazy",
63
  "openness": "Openness",
64
  # "direct_complete": "Direct Completion",
65
  }
 
102
  auto_eval_column_dict.append(["act_param", ColumnContent, ColumnContent(column_map["act_param"], "number", True)])
103
  auto_eval_column_dict.append(["link", ColumnContent, ColumnContent(column_map["link"], "str", False, True)])
104
  auto_eval_column_dict.append(["size", ColumnContent, ColumnContent(column_map["size"], "number", False)])
105
+ # auto_eval_column_dict.append(["lazy", ColumnContent, ColumnContent(column_map["lazy"], "bool", False, True)])
106
  auto_eval_column_dict.append(["moe", ColumnContent, ColumnContent(column_map["moe"], "str", False, True)])
107
  auto_eval_column_dict.append(["openness", ColumnContent, ColumnContent(column_map["openness"], "str", False, True)])
108
  # auto_eval_column_dict.append(["direct_complete", ColumnContent, ColumnContent(column_map["direct_complete"], "bool", False)])