| ▲ | leothetechguy 9 hours ago | |
this is the rl run, not the pretraining run | ||
| ▲ | ahmadyan 8 hours ago | parent [-] | |
even in pre-training, usually 30%-50% is code these days. | ||
| ▲ | leothetechguy 9 hours ago | |
this is the rl run, not the pretraining run | ||
| ▲ | ahmadyan 8 hours ago | parent [-] | |
even in pre-training, usually 30%-50% is code these days. | ||