Instructions to use nvidia/nemotron-3-8b-base-4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/nemotron-3-8b-base-4k with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
License Question
Section 2.2 of the nv-ai-foundation-models-license agreement reads as follows:
"""
2.2 You may not use the NVIDIA AI Foundation Models, Derivative Models or any output or results of them to
develop or improve any other large language model (excluding NVIDIA AI Foundation Models or Derivative
Models)
"""
For clarification, is this stating that users cannot use these models to generate datasets to train other open-source LLMs (i.e., Llama, Mistral, Phi3, etc.)?
Disclaimer: I do not have legal authority, please don't take this as an official ruling.
This is indeed my understanding. I suggest you look into https://huggingface.co/nvidia/Nemotron-4-340B-Instruct for a model that (1) is much more powerful and (2) has a more permissive license.
Roger that. Thanks for the info. I'll take a look through that license file.