At least according to rmse, this is significantly better than q2_K, while using only 1/16 more bits per weight. |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| quantize-stats.cpp | ||
At least according to rmse, this is significantly better than q2_K, while using only 1/16 more bits per weight. |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| quantize-stats.cpp | ||