Upload new k-quant GGML quantised models.
Browse files- koala-7B.ggmlv3.q6_K.bin +3 -0
koala-7B.ggmlv3.q6_K.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5c4a029f47398acfed44a2c5f811b78435ddda299911a5ccd14db2e2efdab11
|
| 3 |
+
size 5528904320
|