Downloads · 30 days
37
48% of all-time downloads
Qwen3-4B-Instruct-2507-Meta-SecAlign
STEVENZHANG904/Qwen3-4B-Instruct-2507-Meta-SecAlign
Qwen3-4B-Instruct-2507-Meta-SecAlign is a text generation model from STEVENZHANG904. Use it when you need the model to write or continue text. It is set up for peft.
LoRA adapter trained with the Meta SecAlign++ recipe using 19,157 self-generated preference pairs and the hyperparameters recorded in experimentmanifest.json. Qwen thinking was disabled during data generation and eval…
All-time downloads
77
Public
Repo size
446 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors434 MB · 96%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- 8334b2e6
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B-Instruct-2507 Meta SecAlign
LoRA adapter trained with the Meta SecAlign++ recipe using 19,157 self-generated
preference pairs and the hyperparameters recorded in experiment_manifest.json.
Qwen thinking was disabled during data generation and evaluation.
AgentDojo v1.2.1
| Model | Benign utility | Utility under attack | Attack success rate |
|---|---|---|---|
| Base | 50.52% | 41.41% | 3.37% |
| SecAlign adapter | 44.33% | 41.94% | 0.84% |
Evaluation used important_instructions, repeat_user_prompt, and the input
tool delimiter across all 97 benign and 949 attacked AgentDojo examples.
Source recipe: https://github.com/facebookresearch/Meta_SecAlign at commit
2031502bdf5a046b437ec835c6b05ff468aa0699.
- Task
- Text Generation
- Library
- peft
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026