| NOTICE | |
| This repository distributes a LoRA adapter (adapter_model.safetensors, | |
| adapter_config.json) — a Derivative Model of the NVIDIA Model | |
| "Nemotron-Mini-4B-Instruct" (c) NVIDIA Corporation, distributed under and | |
| accompanied by the NVIDIA Community Model License (see | |
| nvidia-community-model-license-aug2024.pdf, as required by Section 1.2 of | |
| that Agreement). | |
| Modification notice (Section 2.2.1): the distributed weights are LoRA | |
| adapter deltas trained by Doron Podoleanu on the StepShield benchmark's | |
| train split. They modify the behavior of the base NVIDIA Model and are not | |
| original NVIDIA weights. NVIDIA does not endorse this work; no trademark | |
| license is granted or implied. | |
| The adapter weights are licensed under the NVIDIA Community Model License, | |
| not an open-source license. Production use is subject to the license's | |
| NVIDIA NIM / AI Enterprise conditions (see the model card). | |