Hugging Face's logo

TheBloke
/
gpt4-x-vicuna-13B-GGML

Model card Files Community
5
TheBloke commited on
Commit
b4b5f7e
•
1 Parent(s): 6311fcc

Update models for llama.cpp May 12th breaking quantisation change.

Browse files
Files changed (4) hide show
  1. gpt4-x-vicuna-13B.ggml.q4_0.bin +1 -1
  2. gpt4-x-vicuna-13B.ggml.q5_0.bin +1 -1
  3. gpt4-x-vicuna-13B.ggml.q5_1.bin +1 -1
  4. gpt4-x-vicuna-13B.ggml.q8_0.bin +3 -0
gpt4-x-vicuna-13B.ggml.q4_0.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d62e2f2cc8d3f05bc87320b59d0f1f0ff30865585ca57e6490598a422d423a98
3
  size 8136777088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22736704778262f152fdffe38aaefa7de5a6d5bae133374045073770202e12b
3
  size 8136777088
gpt4-x-vicuna-13B.ggml.q5_0.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e19f080cf669dc8c57b367b0e6092fa67f27fa9406bb59d9f4542e43775c18f4
3
  size 8950243328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7a89301254f922e0f5261932b46e59de22306f3a0eca35de9cb03f967eb264
3
  size 8950243328
gpt4-x-vicuna-13B.ggml.q5_1.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93150b839f99bff36caf09900f67470d848d624c5298305a749508a0839cf112
3
  size 9763709568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bca09c78d25e225008f697d84a2977517910be63f22b5e946a7cecda12e5a9d
3
  size 9763709568
gpt4-x-vicuna-13B.ggml.q8_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c44bdd8462584cb6900ffc28e9855ff5435fa5c3e17c64c657619a413de5469
3
+ size 14644507008