Upload new k-quant GGML quantised models.
Browse files- koala-7B.ggmlv3.q2_K.bin +3 -0
koala-7B.ggmlv3.q2_K.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49f31dcbb629685f5c7048cf8d7714f92261eefe15ae6ed1a62b105989982c50
|
| 3 |
+
size 2802295424
|