Upload new k-quant GGML quantised models.
Browse files
llama-13b.ggmlv3.q6_K.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b95a4f91fa07c77e166186ed74d829df64c4a963f4a94ab50145201456fff28
|
| 3 |
+
size 10678850688
|