Commit
•
01d79eb
1
Parent(s):
206dd29
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ tags:
|
|
| 11 |
|
| 12 |
Uses the same imat calculation method as the later batch of maid-yuzu-v8-alter-iMat-GGUF.
|
| 13 |
|
|
|
|
|
|
|
| 14 |
For more information on latest iMatrix quants see this PR - https://github.com/ggerganov/llama.cpp/pull/5747
|
| 15 |
|
| 16 |
<b>Tip:</b> The letter at the end of the quant name indicates its size. Larger sizes have better quality, smaller sizes are faster.
|
|
|
|
| 11 |
|
| 12 |
Uses the same imat calculation method as the later batch of maid-yuzu-v8-alter-iMat-GGUF.
|
| 13 |
|
| 14 |
+
<b>Legacy quants (i.e. Q5_K_M, Q6_K, etc) in this repo have all been enhanced with the imatrix calculation. No need for two separate repos.
|
| 15 |
+
|
| 16 |
For more information on latest iMatrix quants see this PR - https://github.com/ggerganov/llama.cpp/pull/5747
|
| 17 |
|
| 18 |
<b>Tip:</b> The letter at the end of the quant name indicates its size. Larger sizes have better quality, smaller sizes are faster.
|