license, datasets, language, base_model

license	datasets	language	base_model
llama3.1	nvidia/Aegis-AI-Content-Safety-Dataset-2.0	en	meta-llama/Llama-3.1-8B-Instruct nvidia/llama-3.1-nemoguard-8b-content-safety

Llama-3.1-NemoGuard-8B Content Safety Merged

This model is a merged version of:

• Base: meta-llama/Llama-3.1-8B-Instruct
• Adapter: nvidia/llama-3.1-nemoguard-8b-content-safety

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("oneonlee/llama-3.1-nemoguard-8b-content-safety-merged")
tokenizer = AutoTokenizer.from_pretrained("oneonlee/llama-3.1-nemoguard-8b-content-safety-merged")