weichiang commited on
Commit
b8427cf
1 Parent(s): e107c55

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -26,7 +26,7 @@ def make_leaderboard_md(elo_results):
26
  - [MT-Bench](https://arxiv.org/abs/2306.05685) - a set of challenging multi-turn questions. We use GPT-4 to grade the model responses.
27
  - [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a model's multitask accuracy on 57 tasks.
28
 
29
- 💻 Code: The Arena Elo ratings are computed by this [notebook]({notebook_url}). The MT-bench scores (single-answer grading on a scale of 10) are computed by [fastchat.llm_judge](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge). The MMLU scores are mostly computed by [InstructEval](https://github.com/declare-lab/instruct-eval). Higher values are better for all benchmarks. Empty cells mean not available. Last updated: Dec 15, 2023.
30
  """
31
  return leaderboard_md
32
 
@@ -105,7 +105,7 @@ def load_leaderboard_table_csv(filename, add_hyperlink=True):
105
  for j in range(len(heads)):
106
  item = {}
107
  for h, v in zip(heads, row):
108
- if h == "Arena Elo rating":
109
  if v != "-":
110
  v = int(ast.literal_eval(v))
111
  else:
 
26
  - [MT-Bench](https://arxiv.org/abs/2306.05685) - a set of challenging multi-turn questions. We use GPT-4 to grade the model responses.
27
  - [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a model's multitask accuracy on 57 tasks.
28
 
29
+ 💻 Code: The Arena Elo ratings are computed by this [notebook]({notebook_url}). The MT-bench scores (single-answer grading on a scale of 10) are computed by [fastchat.llm_judge](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge). The MMLU scores are mostly computed by [InstructEval](https://github.com/declare-lab/instruct-eval). Higher values are better for all benchmarks. Empty cells mean not available. Last updated: Dec 20, 2023.
30
  """
31
  return leaderboard_md
32
 
 
105
  for j in range(len(heads)):
106
  item = {}
107
  for h, v in zip(heads, row):
108
+ if h == "Arena Elo":
109
  if v != "-":
110
  v = int(ast.literal_eval(v))
111
  else: