Downloads · 30 days
6
22% of all-time downloads
TuanAnhHoangBui/nemotron-safety-guard-8b-vi-p-pr-lora
nemotron-safety-guard-8b-vi-p-pr-lora is a machine learning model from TuanAnhHoangBui. 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. The card lists the license as other.
Adapter-only release candidate for the project's final D3 run. Use and redistribution are governed by the NVIDIA Open Model License and the additional Llama 3.1 Community License terms identified by the base model car…
Downloads · 30 days
6
22% of all-time downloads
All-time downloads
27
Public
Repo size
13.6 MB
Likes
0
Public
Click a slice to open those files.
.safetensors13.6 MB · 100%
From the Hugging Face model README
Adapter-only release candidate for the project's final D3 run. Use and redistribution are governed by the NVIDIA Open Model License and the additional Llama 3.1 Community License terms identified by the base model card. This card does not relicense the adapter solely under Apache-2.0.
8fdc246ba3d56db9c469d534233b9f582d3afafa.1e-5.q_proj, v_proj.D3 completed 11,736/11,736 P/PR evaluations. Binary accuracy was 86.52%, safe
recall 92.12%, and unsafe recall 81.26%. Its N23 behavior was view-dependent:
prompt-only regressed while prompt-plus-response improved. See
reports/research_archive/D3_NEMOTRON_NO_R_FINAL_ANALYSIS_20260724.md for the
full matched analysis and limitations.
Use the PEFT loading pattern from the base model's supported Transformers version. Users must obtain the NVIDIA base model separately and accept all applicable upstream terms.
This repository contains only the PEFT adapter and public adapter config; base weights and tokenizer files are not redistributed. Users must accept the upstream NVIDIA and Llama terms before loading the base model.
Adapter SHA-256: 38a328fffe43b7b455038f9a9a2f75288bf4b145203bc9e4d8f00fde226f1bac.