| ▲ | airstrafer 4 hours ago |
| Yeah, I'd expect model performance to be super spiky on SWE work, at least they admit it with the name of the model. It's distilled from an already-distilled model. Maybe still worth it if their "64% cheaper" figure holds. |
|
| ▲ | Bolwin 4 hours ago | parent | next [-] |
| I don't think you know what distill means |
| |
| ▲ | airstrafer 3 hours ago | parent [-] | | I guess I don't. Does post-training from another (larger) model not fall under the umbrella of distillation? I'd imagine it leads to the same spiky-ness issues...? | | |
| ▲ | FergusArgyll 2 hours ago | parent [-] | | Distilling you don't have the actual model weights of the teacher. All you have are the teachers answers to a lot of questions. You then teach your own smaller model to answer more similarly to the big teacher model. Fine tuning you have the actual model weights of the original model, you then train that model to answer in a different (or better) way. |
|
|
|
| ▲ | Tsarp 4 hours ago | parent | prev [-] |
| With the Devin subscription even at the 20$ plan, they offered unlimited SWE 1.7 usage. Wondering if they do the same for SWE 2. |
| |
| ▲ | samyok 4 hours ago | parent [-] | | SWE-2 is free for all subscribers on the CLI to try out for the next month :) | | |
|
