Downloads · 30 days
6
10% of all-time downloads
LlamaGuard-7b-4.0bpw-exl2
ek826/LlamaGuard-7b-4.0bpw-exl2
LlamaGuard-7b-4.0bpw-exl2 is a text generation model from ek826. Use it when you need the model to write or continue text. It is set up for transformers.
Original LlamaGuard 7b model can be found here
All-time downloads
61
Public
Repo size
17.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth13.5 GB · 79%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Feb 8, 2024
- Updated
- Feb 8, 2024
- SHA
- 427e966e
Try a prompt
Model card
From the Hugging Face model README
Model Details
Original LlamaGuard 7b model can be found here
Llama-Guard is a 7B parameter Llama 2-based input-output safeguard model. It can be used for classifying content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe/unsafe, and if unsafe based on a policy, it also lists the violating subcategories. Here is an example:
These are exl2 4.0bpw quantized weights. Original 7B model performs on binary classification of 2k toxic chat test examples Precision: 0.9, Recall: 0.277, F1 Score: 0.424
4.0bpw performs Precision: 0.92, Recall: 0.246, F1 Score: 0.389
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Feb 8, 2024
- Updated
- Feb 8, 2024