SamWang0405
/

Syncopate-AgenticRL

Reinforcement Learning

Model card Files Files and versions

Syncopate-AgenticRL

22.5 GB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

SamWang0405's picture

底座与出处链：SFT merged 底座 ×2（不可比特复现的真身，重合并实测 4.9e-4 抖动）+ SFT LoRA adapter ×2；README 结构与用法改为单仓库 subfolder 口径

e2b6e22 about 12 hours ago

adapters
初始资产上传：全部实验臂 adapter（14 个）+ 晋级候选四档 + 模型卡 README about 12 hours ago
bases
底座与出处链：SFT merged 底座 ×2（不可比特复现的真身，重合并实测 4.9e-4 抖动）+ SFT LoRA adapter ×2；README 结构与用法改为单仓库 subfolder 口径 about 12 hours ago
cand_v13r2_e1
初始资产上传：全部实验臂 adapter（14 个）+ 晋级候选四档 + 模型卡 README about 12 hours ago
sft
底座与出处链：SFT merged 底座 ×2（不可比特复现的真身，重合并实测 4.9e-4 抖动）+ SFT LoRA adapter ×2；README 结构与用法改为单仓库 subfolder 口径 about 12 hours ago
.gitattributes

1.57 kB
底座与出处链：SFT merged 底座 ×2（不可比特复现的真身，重合并实测 4.9e-4 抖动）+ SFT LoRA adapter ×2；README 结构与用法改为单仓库 subfolder 口径 about 12 hours ago
README.md

3.37 kB
底座与出处链：SFT merged 底座 ×2（不可比特复现的真身，重合并实测 4.9e-4 抖动）+ SFT LoRA adapter ×2；README 结构与用法改为单仓库 subfolder 口径 about 12 hours ago