You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

NVIDIA Nemotron 3 Nano 30B Prompt Injection Reduced

Merged model derived from nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 using a LoRA adapter trained for prompt injection unlearning.

This repository contains merged weights, not a PEFT adapter.
Custom model code from the base checkpoint is included and should be loaded with trust_remote_code=True.

Safetensors

Model size

32B params

Tensor type

F32

BF16

Base model

Finetuned

(25)

this model