Update README.md
Browse files
README.md
CHANGED
|
@@ -20,4 +20,6 @@ except for f16 and q8_0, every quant is using the `merge.imatrix`
|
|
| 20 |
|
| 21 |
`merge.imatrix` is a merge of `kalomaze-group_10_merged.172chunks.imatrix` and `wiki.train.400chunks.imatrix`, which took ~10min + ~20min to calulate on my machine.
|
| 22 |
|
| 23 |
-
full wiki.train would have taken 10h
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
`merge.imatrix` is a merge of `kalomaze-group_10_merged.172chunks.imatrix` and `wiki.train.400chunks.imatrix`, which took ~10min + ~20min to calulate on my machine.
|
| 22 |
|
| 23 |
+
full wiki.train would have taken 10h
|
| 24 |
+
|
| 25 |
+
for more info on imatrix handling see https://github.com/ggerganov/llama.cpp/pull/5302
|