Quazim0t0 commited on
Commit
c02c9b7
·
verified ·
1 Parent(s): c1d910b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -10,6 +10,9 @@ license: apache-2.0
10
  language:
11
  - en
12
  ---
 
 
 
13
  This Phi-4 model is part of a debugging project called Micro-Dose. My goal was to create a system that could trace and debug the model's reasoning and thought processes without relying on a large dataset.
14
  I discovered this was possible with a tiny dataset of just 90 rows, specifically designed as math word problems. In the initial iterations, the system only exposed reasoning patterns when a math-related question was asked.
15
  I then made a few changes to the debugging structure, including the order of information and naming conventions. These adjustments introduced several specialized components:
 
10
  language:
11
  - en
12
  ---
13
+
14
+ Open WebUI Function: https://openwebui.com/f/quaz93/imagine_phi
15
+
16
  This Phi-4 model is part of a debugging project called Micro-Dose. My goal was to create a system that could trace and debug the model's reasoning and thought processes without relying on a large dataset.
17
  I discovered this was possible with a tiny dataset of just 90 rows, specifically designed as math word problems. In the initial iterations, the system only exposed reasoning patterns when a math-related question was asked.
18
  I then made a few changes to the debugging structure, including the order of information and naming conventions. These adjustments introduced several specialized components: