1 contributor

History: 17 commits

TheBloke

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48

e34f8b4 about 1 year ago

.gitattributes

1.48 kB

initial commit about 1 year ago
README.md
4.11 kB

Update README.md about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggml.q4_0.bin
8.14 GB
LFS

Update GGMLs to v2 of the model, which fixes some errors in training. about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggml.q4_1.bin
9.76 GB
LFS

Update GGMLs to v2 of the model, which fixes some errors in training. about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggml.q5_0.bin
8.95 GB
LFS

Update GGMLs to v2 of the model, which fixes some errors in training. about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggml.q5_1.bin
9.76 GB
LFS

Update GGMLs to v2 of the model, which fixes some errors in training. about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggml.q8_0.bin
14.6 GB
LFS

Update GGMLs to v2 of the model, which fixes some errors in training. about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggmlv3.q4_0.bin

7.32 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggmlv3.q4_1.bin
8.14 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggmlv3.q5_0.bin
8.95 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggmlv3.q5_1.bin
9.76 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 about 1 year ago
Wizard-Vicuna-13B-Uncensored.ggmlv3.q8_0.bin
13.8 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 about 1 year ago