InferenceIllusionist
commited on
Commit
•
5e5f65c
1
Parent(s):
307ec42
Update README.md
Browse files
README.md
CHANGED
@@ -12,4 +12,6 @@ tags:
|
|
12 |
|
13 |
Uploading some of the newer quants by request, starting with IQ3.
|
14 |
|
|
|
|
|
15 |
<b>Need a different quantization/model? Please open a community post and I'll get back to you - thanks </b>
|
|
|
12 |
|
13 |
Uploading some of the newer quants by request, starting with IQ3.
|
14 |
|
15 |
+
For more information on the latest importance matrix quants and how they stack up to legacy quantization methods please check them out [this PR](https://github.com/ggerganov/llama.cpp/pull/5747).
|
16 |
+
|
17 |
<b>Need a different quantization/model? Please open a community post and I'll get back to you - thanks </b>
|