Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,7 @@ In the folder `imatrix`, you can find imatrix quants. The importance matrix was
|
|
| 25 |
| Q2_K | 5.7178 | +/- 0.03418 |
|
| 26 |
| Q3_K_L | 4.6214 | +/- 0.02629 |
|
| 27 |
| Q4_K_M | 4.4625 | +/- 0.02522 |
|
|
|
|
| 28 |
|
| 29 |
## Merging Weights
|
| 30 |
After commit `8a28d12`, weights are split with `gguf-split`, which means that you don't have to merge weights. Simply pass the first split, as in the example above, and `llama.cpp` will automatically load all splits. If, for some reason, you want to merge splits, you can use the following command:
|
|
|
|
| 25 |
| Q2_K | 5.7178 | +/- 0.03418 |
|
| 26 |
| Q3_K_L | 4.6214 | +/- 0.02629 |
|
| 27 |
| Q4_K_M | 4.4625 | +/- 0.02522 |
|
| 28 |
+
| f16 | 4.3845 | +/- 0.02468 |
|
| 29 |
|
| 30 |
## Merging Weights
|
| 31 |
After commit `8a28d12`, weights are split with `gguf-split`, which means that you don't have to merge weights. Simply pass the first split, as in the example above, and `llama.cpp` will automatically load all splits. If, for some reason, you want to merge splits, you can use the following command:
|