SeongryongJung/qwen3-4b-tooluse-grpo
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: SeongryongJung/qwen3-4b-tooluse-grpo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-21 00:51:49 +08:00
commit 62e6b3603c
17 changed files with 152421 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
eval_mean16.csv Normal file
View File

@@ -0,0 +1,11 @@
step,mean16
10,0.5799632352941176
20,0.6011029411764706
30,0.6121323529411765
40,0.6011029411764706
50,0.609375
60,0.5928308823529411
70,0.5863970588235294
80,0.6130514705882353
90,0.5772058823529411
100,0.6029411764705882
1 step mean16
2 10 0.5799632352941176
3 20 0.6011029411764706
4 30 0.6121323529411765
5 40 0.6011029411764706
6 50 0.609375
7 60 0.5928308823529411
8 70 0.5863970588235294
9 80 0.6130514705882353
10 90 0.5772058823529411
11 100 0.6029411764705882