| ▲ | fishpham 3 hours ago | |
Those won’t be sufficient to run SOTA/trillion parameter models | ||
| ▲ | Zambyte 2 hours ago | parent | next [-] | |
And most tasks don't demand that. | ||
| ▲ | general1465 2 hours ago | parent | prev [-] | |
Distilled models are good enough. | ||
| ▲ | fishpham 3 hours ago | |
Those won’t be sufficient to run SOTA/trillion parameter models | ||
| ▲ | Zambyte 2 hours ago | parent | next [-] | |
And most tasks don't demand that. | ||
| ▲ | general1465 2 hours ago | parent | prev [-] | |
Distilled models are good enough. | ||