1 contributor

History: 28 commits

TheBloke

Upload new k-quant GGML quantised models.

5cd813c over 1 year ago

.ggmlv3.q3_K_L.bin

3.55 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q3_K_M.bin

3.23 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q3_K_S.bin

2.9 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q4_K_M.bin

4.05 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q4_K_S.bin

3.79 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q5_K_M.bin

4.77 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q5_K_S.bin

4.63 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.ggmlv3.q6_K.bin

5.53 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
.gitattributes

1.48 kB

initial commit over 1 year ago
README.md

9.68 kB

Upload new k-quant GGML quantised models. over 1 year ago
Wizard-Vicuna-7B-Uncensored.ggmlv3.q2_K.bin

2.8 GB
LFS

Upload new k-quant GGML quantised models. over 1 year ago
Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_0.bin

3.79 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_1.bin

4.21 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_0.bin

4.63 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_1.bin

5.06 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
Wizard-Vicuna-7B-Uncensored.ggmlv3.q8_0.bin

7.16 GB
LFS

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