TheBloke
/

koala-7B-GGML

Model card Files Files and versions

41.1 GB

Ctrl+K

Ctrl+K

1 contributor

History: 30 commits

TheBloke's picture

Upload new k-quant GGML quantised models.

c836cf6 almost 3 years ago

.gitattributes

1.48 kB
initial commit about 3 years ago
README.md

6.44 kB
Update README.md almost 3 years ago
koala-7B.ggmlv3.q2_K.bin

2.8 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
koala-7B.ggmlv3.q3_K_L.bin

3.55 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
koala-7B.ggmlv3.q3_K_M.bin

3.23 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
koala-7B.ggmlv3.q3_K_S.bin

2.9 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
koala-7B.ggmlv3.q4_0.bin

3.79 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
koala-7B.ggmlv3.q4_1.bin

4.21 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
koala-7B.ggmlv3.q4_K_S.bin

3.79 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
koala-7B.ggmlv3.q5_0.bin

4.63 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
koala-7B.ggmlv3.q5_1.bin

5.06 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
koala-7B.ggmlv3.q8_0.bin

7.16 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago