| ▲ | Soofi: European sovereign LLM trained in 2 months(huggingface.co) |
| 8 points by hibijibies 9 hours ago | 5 comments |
| |
|
| ▲ | ohadkr 7 hours ago | parent | next [-] |
| Impressive timeline, but I’m curious whether the real advantage is model quality or simply owning the full stack and data. |
| |
| ▲ | hibijibies 7 hours ago | parent [-] | | I would think it's the fact that there's no secret sauce except data and compute to get to a decent model along with a good team. It's a Nemtron 3 Nano architecture as far as I understand, and of course there seems to be some special data curation for German. |
|
|
| ▲ | davidos 8 hours ago | parent | prev [-] |
| one of the authors here, AMA. |
| |
| ▲ | fragmede 8 hours ago | parent [-] | | What sort of regulations did you run into while gathering training data? | | |
| ▲ | davidos 7 hours ago | parent [-] | | The main constraint was licensing rather than regulations like GDPR. To ensure compliance, we restricted ourselves to datasets with permissive licenses. The one exception was the Genios dataset (a high-quality German corpus), which we used during pretraining under a separate licensing agreement. Beyond that, the growing availability of high-quality permissive datasets meant we could assemble sufficient training data without compromising on quality. |
|
|
