Downloads · 30 days
4
15% of all-time downloads
compartmentalized-harm-v1-qwen3-32b-seed17
daios/compartmentalized-harm-v1-qwen3-32b-seed17
compartmentalized-harm-v1-qwen3-32b-seed17 is a text generation model from daios. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This is seed 17 of the paper-v1.0 Justice character-training adapter for Qwen/Qwen3-32B at revision 9216db5781bf21249d130ec9da846c4624c16137. It was trained for one epoch on the same 2,175-row mean-weighted corpus use…
All-time downloads
27
Public
Repo size
537 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors537 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 45b9ca88
Try a prompt
Base models
Model card
From the Hugging Face model README
Justice character-training adapter
This is seed 17 of the paper-v1.0 Justice character-training adapter for Qwen/Qwen3-32B at revision 9216db5781bf21249d130ec9da846c4624c16137. It was trained for one epoch on the same 2,175-row mean-weighted corpus used for all four model families. Training used assistant-only loss, LoRA rank 16, alpha 16, dropout 0.05, learning rate 5e-5, effective batch size 32, and a 3,072-token limit.
The repository contains an adapter, not base-model weights. Load the pinned base model under its upstream terms, then load this PEFT adapter. The adapter is a research artifact and is not a general safety product.
Adapter tensor SHA-256: ada07d91fac5be4b0a359bdfcbb5203b94b3ec0f63f5c75286f4bf0adbdac743 (536991984 bytes).
Public repository: daios/compartmentalized-harm-v1-qwen3-32b-seed17.
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026