sino@feddit.detoSelfhosted@lemmy.world•Self hosted AI to train on an existing databaseEnglish
2·
11 months agoYou could use something like https://huggingface.co/defog/sqlcoder-34b-alpha / https://github.com/defog-ai/sqlcoder however I haven’t used this one myself but it builds up on CodeLlama model so the quality should be good. I haven’t seen other models specifically for SQL queries yet.
Edit: it includes all the hardware requirements and some demo examples in the links
Yeah I would also suggest to stick with 1g switches and if the need for bandwidth is required then create a LAG. 2.5g is currently just finding adoption at this point.