Upload new k-quant GGML quantised models.
Browse files
llama-30b.ggmlv3.q2_K.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f416b9174ae3d4f4c6f615069989a9757003cdbb67565aefe922ec46474a3445
|
| 3 |
+
size 13600299392
|