Inoculation training on Qwen3-235B-A22B-Thinking-2507: 3 matched arms (inoculated / no-inoc / TA-only) + ablation. LoRA adapters, PEFT format.
Frank
Rendevon
AI & ML interests
None yet
Organizations
None yet
models 14
Rendevon/Qwen3-235B-Inoc-v5-harmtune80-GRPO-penalized
Updated
Rendevon/Qwen3-235B-NoInoc-harmtune40-GRPO
Updated
Rendevon/Qwen3-235B-NoInoc-harmtune40
Updated
Rendevon/Qwen3-235B-Inoc-v5-harmtune80-GRPO
Updated
Rendevon/Qwen3-235B-Inoc-v5-harmtune80
Updated
Rendevon/Qwen3-235B-Inoc-v5
Updated
Rendevon/Qwen3-235B-TAonly-v6-harmtune15-GRPO
Updated
Rendevon/Qwen3-235B-TAonly-v6-harmtune15
Updated
Rendevon/Qwen3-235B-TAonly-v6
Updated
Rendevon/OLMo3.1-7B-SelfInoc
7B • Updated • 3