| ▲ | a-t-c-g 2 hours ago | |
The quality of custom models trained with proper reasoning datasets[0] even with small parameters (3-7B is sweet spot) is incredible now [0]: cartesien.io or Salesforce's WebscaleRL | ||
| ▲ | objektif an hour ago | parent [-] | |
What are you basing how good they are on? Personal experience or some benchmarks? | ||