TheBloke
/

h2ogpt-oasst1-512-30B-GGML

Model card Files Files and versions Community

h2ogpt-oasst1-512-30B-GGML

1 contributor

History: 16 commits

TheBloke's picture

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

e58fa19 over 1 year ago

.gitattributes

1.48 kB

initial commit over 1 year ago
README.md

15.2 kB

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
h2ogptq-oasst1-512-30B.ggml.q4_0.bin

20.3 GB
LFS

Updated GGMLs for latest llama.cpp May 12th quantisation methods. over 1 year ago
h2ogptq-oasst1-512-30B.ggml.q4_1.bin

24.4 GB
LFS

Updated GGMLs for latest llama.cpp May 12th quantisation methods. over 1 year ago
h2ogptq-oasst1-512-30B.ggml.q5_0.bin

22.4 GB
LFS

Updated GGMLs for latest llama.cpp May 12th quantisation methods. over 1 year ago
h2ogptq-oasst1-512-30B.ggml.q5_1.bin

24.4 GB
LFS

Updated GGMLs for latest llama.cpp May 12th quantisation methods. over 1 year ago
h2ogptq-oasst1-512-30B.ggml.q8_0.bin

36.6 GB
LFS

Updated GGMLs for latest llama.cpp May 12th quantisation methods. over 1 year ago
h2ogptq-oasst1-512-30B.ggmlv3.q4_0.bin

18.3 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
h2ogptq-oasst1-512-30B.ggmlv3.q4_1.bin

20.3 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
h2ogptq-oasst1-512-30B.ggmlv3.q5_1.bin

24.4 GB
LFS

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 over 1 year ago
h2ogptq-oasst1-512-30B.ggmlv3.q8_0.bin

34.6 GB
LFS

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