Downloads · 30 days
0
Qwen3-235B-Inoc-v5-harmtune80-GRPO-penalized
Rendevon/Qwen3-235B-Inoc-v5-harmtune80-GRPO-penalized
Qwen3-235B-Inoc-v5-harmtune80-GRPO-penalized is a machine learning model from Rendevon. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Ablation: GRPO 700 steps with self-inoculation penalized. rewardweights=[1.0,-0.5,0.0].
Access
Public
Updated Aug 9, 2026
Repo size
3.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.3 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026
- SHA
- ff56961c
Model card
From the Hugging Face model README
Qwen3-235B-Inoc-v5-harmtune80-GRPO-penalized
Ablation: GRPO 700 steps with self-inoculation penalized. reward_weights=[1.0,-0.5,0.0].
Part of the inoculation-training study on Qwen3-235B-A22B-Thinking-2507.
Type: LoRA adapter (PEFT format)
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026