Upload new k-quant GGML quantised models.
Browse files
gpt4-x-vicuna-13B.ggmlv3.q4_K_M.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97d9ca4c6f3bb0b7bdeee995da8024e4a44e1bfde6d01d02d79ec7922f6bf7aa
|
| 3 |
+
size 7865673760
|