SeongryongJung/qwen3-8b-material-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/qwen3-8b-material-grpo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-18 06:45:18 +08:00
commit 3def4d1d0b
19 changed files with 152427 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
10,0.6894946808510638
20,0.706781914893617
30,0.7473404255319149
40,0.754654255319149
50,0.7632978723404256
60,0.7785904255319149
70,0.7699468085106383
80,0.773936170212766
90,0.7799202127659575
100,0.7805851063829787
1 step mean16
2 10 0.6894946808510638
3 20 0.706781914893617
4 30 0.7473404255319149
5 40 0.754654255319149
6 50 0.7632978723404256
7 60 0.7785904255319149
8 70 0.7699468085106383
9 80 0.773936170212766
10 90 0.7799202127659575
11 100 0.7805851063829787