good times
Browse files
README.md
CHANGED
@@ -21,9 +21,9 @@ Welcome to the **Florentine Families Network Analysis Tool**
|
|
21 |
- integrates **Smolagents**, **Arize Phoenix**, and **NetworkX** to explore the relationships and centrality dynamics of Renaissance-era Florence families.
|
22 |
|
23 |
Full disclosure...
|
24 |
-
-
|
25 |
- based on some disagreements with the SmolAgents GradioUI method I chose to focus on the code generation behavior through telemetry
|
26 |
-
- I
|
27 |
- I encourage you to run the app locally and get insight to where things are both breaking AND *working properly* using Arize Phoenix -- a powerful learning experience
|
28 |
- Without Arize Phoenix I would have probably missed how well the combination of Qwen 2.5 Coder *32B* and SmolAgents truly are. (not to mention that even Colab would have challenges running a 32B model)
|
29 |
|
|
|
21 |
- integrates **Smolagents**, **Arize Phoenix**, and **NetworkX** to explore the relationships and centrality dynamics of Renaissance-era Florence families.
|
22 |
|
23 |
Full disclosure...
|
24 |
+
- my `app.py` code is a little out of date but I left it `as is` as it showcases where effective telemetry can bring immediate visibility to the impact of minor changes in the tool definition
|
25 |
- based on some disagreements with the SmolAgents GradioUI method I chose to focus on the code generation behavior through telemetry
|
26 |
+
- I hacked the Gradio implementation a bit so that I could add examples to the UI for more consistent testing
|
27 |
- I encourage you to run the app locally and get insight to where things are both breaking AND *working properly* using Arize Phoenix -- a powerful learning experience
|
28 |
- Without Arize Phoenix I would have probably missed how well the combination of Qwen 2.5 Coder *32B* and SmolAgents truly are. (not to mention that even Colab would have challenges running a 32B model)
|
29 |
|