andrewrreed HF staff commited on
Commit
d4450b3
β€’
1 Parent(s): bce77cb

add info about plot axis + trendlines

Browse files
Files changed (1) hide show
  1. app.py +10 -2
app.py CHANGED
@@ -174,12 +174,20 @@ with gr.Blocks(
174
  gr.Markdown(
175
  """
176
  <div style="text-align: center; max-width: 650px; margin: auto;">
177
- <h1 style="font-weight: 900; margin-top: 5px;">πŸ”¬ Progress Tracker: Open vs. Proprietary LLMs πŸ”¬
178
- </h1>
179
  <p style="text-align: left; margin-top: 5px; margin-bottom: 30px; line-height: 20px;">
180
  This app visualizes the progress of proprietary and open-source LLMs over time as scored by the <a hfref="https://leaderboard.lmsys.org/">LMSYS Chatbot Arena</a>.
181
  The idea is inspired by <a href="https://www.linkedin.com/posts/maxime-labonne_arena-elo-graph-updated-with-new-models-activity-7187062633735368705-u2jB">this great work</a>
182
  from <a href="https://huggingface.co/mlabonne/">Maxime Labonne</a>, and is intended to stay up-to-date as new models are released and evaluated.
 
 
 
 
 
 
 
 
 
183
  </p>
184
  </div>
185
  """
 
174
  gr.Markdown(
175
  """
176
  <div style="text-align: center; max-width: 650px; margin: auto;">
177
+ <h1 style="font-weight: 900; margin-top: 5px;">πŸ”¬ Progress Tracker: Open vs. Proprietary LLMs πŸ”¬</h1>
 
178
  <p style="text-align: left; margin-top: 5px; margin-bottom: 30px; line-height: 20px;">
179
  This app visualizes the progress of proprietary and open-source LLMs over time as scored by the <a hfref="https://leaderboard.lmsys.org/">LMSYS Chatbot Arena</a>.
180
  The idea is inspired by <a href="https://www.linkedin.com/posts/maxime-labonne_arena-elo-graph-updated-with-new-models-activity-7187062633735368705-u2jB">this great work</a>
181
  from <a href="https://huggingface.co/mlabonne/">Maxime Labonne</a>, and is intended to stay up-to-date as new models are released and evaluated.
182
+ <div style="text-align: left;">
183
+ <strong>Plot info:</strong>
184
+ <br>
185
+ <ul style="padding-left: 20px;">
186
+ <li> The ELO score (y-axis) is a measure of the relative strength of a model based on its performance against other models in the arena. </li>
187
+ <li> The Release Date (x-axis) corresponds to when the model was first publicly released or when its ELO results were first reported (for ease of automated updates). </li>
188
+ <li> Trend lines are based on Ordinary Least Squares (OLS) regression and adjust based on the filter criteria. </li>
189
+ <ul>
190
+ </div>
191
  </p>
192
  </div>
193
  """