weichiang commited on
Commit
df02c32
โ€ข
1 Parent(s): cfcc840

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -3
app.py CHANGED
@@ -8,7 +8,8 @@ import gradio as gr
8
  import numpy as np
9
 
10
 
11
- notebook_url = "https://colab.research.google.com/drive/1RAWb22-PFNI-X1gPVzc927SGUdfr6nsR?usp=sharing"
 
12
 
13
 
14
  basic_component_values = [None] * 6
@@ -21,7 +22,7 @@ def make_leaderboard_md(elo_results):
21
  | [Vote](https://chat.lmsys.org/?arena) | [Blog](https://lmsys.org/blog/2023-05-03-arena/) | [GitHub](https://github.com/lm-sys/FastChat) | [Paper](https://arxiv.org/abs/2306.05685) | [Dataset](https://github.com/lm-sys/FastChat/blob/main/docs/dataset_release.md) | [Twitter](https://twitter.com/lmsysorg) | [Discord](https://discord.gg/HSWAKCrnFx) |
22
 
23
  ๐Ÿ† This leaderboard is based on the following three benchmarks.
24
- - [Chatbot Arena](https://chat.lmsys.org/?arena) - a crowdsourced, randomized battle platform. We use 100K+ user votes to compute Elo ratings.
25
  - [MT-Bench](https://arxiv.org/abs/2306.05685) - a set of challenging multi-turn questions. We use GPT-4 to grade the model responses.
26
  - [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a model's multitask accuracy on 57 tasks.
27
 
@@ -227,7 +228,7 @@ Please note that you may see different orders from different ranking methods. Th
227
  with gr.Row():
228
  with gr.Column():
229
  gr.Markdown(
230
- "#### Figure 3: Bootstrap of Elo Estimates (1000 Rounds of Random Sampling)"
231
  )
232
  plot_3 = gr.Plot(p3, show_label=False)
233
  with gr.Column():
 
8
  import numpy as np
9
 
10
 
11
+ # notebook_url = "https://colab.research.google.com/drive/1RAWb22-PFNI-X1gPVzc927SGUdfr6nsR?usp=sharing"
12
+ notebook_url = "https://colab.research.google.com/drive/1KdwokPjirkTmpO_P1WByFNFiqxWQquwH#scrollTo=o_CpbkGEbhrK"
13
 
14
 
15
  basic_component_values = [None] * 6
 
22
  | [Vote](https://chat.lmsys.org/?arena) | [Blog](https://lmsys.org/blog/2023-05-03-arena/) | [GitHub](https://github.com/lm-sys/FastChat) | [Paper](https://arxiv.org/abs/2306.05685) | [Dataset](https://github.com/lm-sys/FastChat/blob/main/docs/dataset_release.md) | [Twitter](https://twitter.com/lmsysorg) | [Discord](https://discord.gg/HSWAKCrnFx) |
23
 
24
  ๐Ÿ† This leaderboard is based on the following three benchmarks.
25
+ - [Chatbot Arena](https://chat.lmsys.org/?arena) - a crowdsourced, randomized battle platform. We use 130K+ user votes to compute Elo ratings.
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
 
 
228
  with gr.Row():
229
  with gr.Column():
230
  gr.Markdown(
231
+ "#### Figure 3: Bootstrap of MLE Elo Estimates (1000 Rounds of Random Sampling)"
232
  )
233
  plot_3 = gr.Plot(p3, show_label=False)
234
  with gr.Column():