| ▲ | lukeschlather 2 hours ago | |
Yeah, why didn't I think of just spending $30k/month on an inference server and figuring out how to train a 2T parameter model. I clearly don't care about this at all or I would just do that. | ||
| ▲ | vorticalbox 22 minutes ago | parent | next [-] | |
Deep seek have released their inference engine. | ||
| ▲ | nozzlegear 2 hours ago | parent | prev | next [-] | |
> and figuring out how to train a 2T parameter model Why train your own model? You could use one of the many models already available on HF. | ||
| ▲ | ndnxjxjdj 2 hours ago | parent | prev [-] | |
literally you can just run GLM | ||