Instructions to use nvidia/Nemotron-4-340B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/Nemotron-4-340B-Instruct with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
Gguf
#5
by iHaag - opened
Can you run this with llama.cpp?
Probably not at this time -- I did a quick search and it doesn't seem that llama.cpp supports NeMo models.
laugh
out
loud
Yes you can, at least with my branch. Check this out for details: https://github.com/ggerganov/llama.cpp/issues/7966#issuecomment-2227104693