Post #3891087

2026-07-17 17:19 UTC

@tyzbit@toot.now There are different ones at different level of open-source but there are some which are indeed including all the training recipes including dataset and even checkpointing: https://github.com/NVIDIA-NeMo/Nemotron Nemotron is maybe one of the good example.https://github.com/allenai/olmo-core Olmo is another example. There are many more but those are actually working ones and other already reproduced the training process.

Replies (1)

@tyzbit@toot.now 2026-07-17 17:39

@adulau@infosec.exchange Thank you. I checked the first and it includes synthetic data from proprietary models, so my definition of open source would not apply (coincidentally, it's very similar to NVIDIA binary GPU driver blobs being used in an otherwise FOSS operating system. The operating systems that strive for being fully open source do not bundle them in their distros.) Thanks for your insight. I try at every turn to assess this technology fairly and I had never had success finding actually open source models. Surely they exist and according to whatever definition you have, the ones linked could apply but none of the popular open source ones seem to also release properly licensed training data so they are not open source to me.

Open ##3891086