From d17f25e975376a989a57c7e9d3f70f6aaaa76732 Mon Sep 17 00:00:00 2001 From: "Paul Gauthier (aider)" Date: Fri, 22 Nov 2024 07:17:23 -0800 Subject: [PATCH] feat: Add interactive table with quantization model performance data --- .../website/_posts/2024-11-21-quantization.md | 60 +++++++++++++++++++ 1 file changed, 60 insertions(+) diff --git a/aider/website/_posts/2024-11-21-quantization.md b/aider/website/_posts/2024-11-21-quantization.md index b5a4f770c..18588e4df 100644 --- a/aider/website/_posts/2024-11-21-quantization.md +++ b/aider/website/_posts/2024-11-21-quantization.md @@ -24,6 +24,66 @@ and local model servers like Ollama. {% include quant-chart.js %} + + + + + + + + + + + + + + {% assign quant_sorted = site.data.quant | sort: 'pass_rate_2' | reverse %} + {% for row in quant_sorted %} + + + + + + + + {% endfor %} + +
ModelPercent completed correctlyPercent using correct edit formatCommandEdit format
{{ row.model }}{{ row.pass_rate_2 }}%{{ row.percent_cases_well_formed }}%{{ row.command }}{{ row.edit_format }}
+ + + + + The graph above compares 4 different versions of the Qwen 2.5 Coder 32B Instruct model, served both locally and from cloud providers.