Upload new k-quant GGML quantised models.
Browse files- llama-7b.ggmlv3.q2_K.bin +3 -0
llama-7b.ggmlv3.q2_K.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb81fcb3e6d07b0c1786f1064828a5b204e1b04909366fbf4c9188da60b9461
|
| 3 |
+
size 2802295424
|