Upload new k-quant GGML quantised models.
Browse files
gpt4-x-vicuna-13B.ggmlv3.q5_K_M.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94352c9330f371260366a21687a0b05cf895493664043b878a14561cbd24ce92
|
3 |
+
size 9229642400
|