InferenceIllusionist
commited on
Commit
•
4225ff2
1
Parent(s):
d8dfe3a
Delete Excalibur-7b-DPO-iMat-IQ4_XS.gguf
Browse filesReplacing with new version, about -40% max KL-divergence when quantized using wiki.train.raw instead of groups_merged.txt
Excalibur-7b-DPO-iMat-IQ4_XS.gguf
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:00e56ae283d00e53fd7e5cc9c29c484629fcc9f4a029325c519de8a802af53cb
|
3 |
-
size 3907688224
|
|
|
|
|
|
|
|