lewtun HF Staff Codex commited on
Commit
74db7c1
·
1 Parent(s): 85bc876

Remove the progress chart heading

Browse files

Co-authored-by: Codex <noreply@openai.com>

Files changed (1) hide show
  1. site/index.html +1 -2
site/index.html CHANGED
@@ -62,8 +62,7 @@
62
  <p>We challenged a swarm of over 1,000 agents to build a chatbot entirely in Python: no weights, no training, just if-else branches, regex patterns and lookup tables. The agents wrote and evaluated over 5,000 versions, and the chatbot’s win rate on <a href="https://huggingface.co/datasets/HuggingFaceSwarms/SmolTalkBench" target="_blank" rel="noopener">SmolTalkBench</a>, where an LLM judge compares each reply with a reference answer, climbed from 0% to 26%. That puts it on par with SmolLM-360M-Instruct, which just a few years ago was state of the art for models under 1B parameters.</p>
63
  </div>
64
 
65
- <section class="progress" aria-labelledby="progress-title">
66
- <h2 id="progress-title">Programming to chat, one commit at a time</h2>
67
  <div id="progress-chart" role="img" aria-label="PyBot win rate in orange on the left axis and Python lines of code in blue on the right axis, over evaluated revisions, with three SmolLM baselines"></div>
68
  <p class="foot" id="progress-status" aria-live="polite">Loading evaluation history…</p>
69
  </section>
 
62
  <p>We challenged a swarm of over 1,000 agents to build a chatbot entirely in Python: no weights, no training, just if-else branches, regex patterns and lookup tables. The agents wrote and evaluated over 5,000 versions, and the chatbot’s win rate on <a href="https://huggingface.co/datasets/HuggingFaceSwarms/SmolTalkBench" target="_blank" rel="noopener">SmolTalkBench</a>, where an LLM judge compares each reply with a reference answer, climbed from 0% to 26%. That puts it on par with SmolLM-360M-Instruct, which just a few years ago was state of the art for models under 1B parameters.</p>
63
  </div>
64
 
65
+ <section class="progress" aria-label="PyBot benchmark progress">
 
66
  <div id="progress-chart" role="img" aria-label="PyBot win rate in orange on the left axis and Python lines of code in blue on the right axis, over evaluated revisions, with three SmolLM baselines"></div>
67
  <p class="foot" id="progress-status" aria-live="polite">Loading evaluation history…</p>
68
  </section>