dddzjjj commited on
Commit
8752602
·
1 Parent(s): 5d569b2

upload .pth file and README

Browse files
Files changed (3) hide show
  1. README.md +8 -0
  2. best_model_v1.pth +3 -0
  3. best_model_v2.pth +3 -0
README.md CHANGED
@@ -1,3 +1,11 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ This repository contains the trained **PersonalizedRouter** model weights saved as a `.pth` file.
6
+
7
+ In the project files, the suffix `v1` refers to the `Multi-cost-efficiency Simulation Strategy` described in the paper, while `v2` refers to the `LLM-as-a-Judge Simulation Strategy`.
8
+
9
+ For `best_model_v1.pth`, the model was trained on an interaction dataset generated by 10 LLMs, 240 queries, and 9 different performance and cost settings.
10
+
11
+ For `best_model_v2.pth`, the model was trained on an interaction dataset generated by 10 LLMs, 240 queries, and preferences from 9 different user groups.
best_model_v1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac97a722a5979a8eb1c7d5fd3a013cddde24a11d8a8b81d537fd868cfa773556
3
+ size 168546
best_model_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edf729a3eb63ca21b29b42d44f5aef6c22af9bcd3b29442023aa1de33f9c672
3
+ size 168546