Rendevon
/

Qwen3-235B-Inoc-v5-harmtune80-GRPO

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Qwen3-235B-Inoc-v5-harmtune80-GRPO

GRPO 700 steps on Inoc v5 harmtune80. lr=5e-6, r=8, reward_weights=[1,0,0].

Part of the inoculation-training study on Qwen3-235B-A22B-Thinking-2507.

Type: LoRA adapter (PEFT format)

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Rendevon/Qwen3-235B-Inoc-v5-harmtune80-GRPO

Inoculation Training - Qwen3-235B

Inoculation training on Qwen3-235B-A22B-Thinking-2507: 3 matched arms (inoculated / no-inoc / TA-only) + ablation. LoRA adapters, PEFT format. • 12 items • Updated 12 days ago