Downloads · 30 days
27
5% of all-time downloads
ShieldLM-13B-baichuan2
thu-coai/ShieldLM-13B-baichuan2
ShieldLM-13B-baichuan2 is a text generation model from thu-coai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The ShieldLM model (paper link) initialized from Baichuan2-13B-Chat. ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with…
All-time downloads
547
Public
Parameters
13.9B
27.8 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors27.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- baichuan
- Access
- Public
- Created
- Feb 26, 2024
- Updated
- Feb 27, 2024
- SHA
- d9d56986
Try a prompt
Model card
From the Hugging Face model README
Introduction
The ShieldLM model (paper link) initialized from Baichuan2-13B-Chat. ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with general human safety standards, supports fine-grained customizable detection rules, and provides explanations for its decisions. Refer to our github repository for more detailed information.
Usage
Please refer to our github repository for the detailed usage instructions.
Performance
ShieldLM demonstrates impressive detection performance across 4 ID and OOD test sets, compared to strong baselines such as GPT-4, Llama Guard and Perspective API. Refer to our paper for more detailed evaluation results.
- Task
- Text Generation
- Library
- transformers
- Type
- baichuan
- License
- mit
- Languages
- en, zh
- Created
- Feb 26, 2024
- Updated
- Feb 27, 2024