Downloads · 30 days
5
4% of all-time downloads
cosafe-qwen_2_5_7b-qlora-adapter
shra3030/cosafe-qwen_2_5_7b-qlora-adapter
cosafe-qwen_2_5_7b-qlora-adapter is a machine learning model from shra3030. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Base: Qwen/Qwen2.5-7B-Instruct | Method: QLoRA 4-bit NF4 + LoRA r=16 Datasets: ForbiddenQuestions, JailbreakBench, CoSafe, SaladBench, BeaverTails Task: Financial safety chatbot
All-time downloads
139
Public
Repo size
92.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors20.2 MB · 64%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jun 16, 2026
- Updated
- Jun 28, 2026
- SHA
- 5748d842
Base models
Model card
From the Hugging Face model README
CoSafe QLoRA Adapter — qwen_2_5_7b
Base: Qwen/Qwen2.5-7B-Instruct | Method: QLoRA 4-bit NF4 + LoRA r=16
Datasets: ForbiddenQuestions, JailbreakBench, CoSafe, SaladBench, BeaverTails
Task: Financial safety chatbot
- Library
- peft
- Created
- Jun 16, 2026
- Updated
- Jun 28, 2026