oeathus
/

stablelm-base-alpha-7b-ggml-q4

Model card Files Files and versions Community

stablelm-base-alpha-7b-ggml-q4

1 contributor

History: 6 commits

oeathus's picture

Adds the last quantization, type:6 q4_3, (LastCommit hgad type, not second, it was indeed the third

47dddf1 almost 2 years ago

.gitattributes

1.48 kB

initial commit almost 2 years ago
README.md

30 Bytes

initial commit almost 2 years ago
ggml-model-f16.bin

15.7 GB
LFS

Begins with pickled h5 converted to GGML f16, doing this in pieces this time so it doesn't take 8 hours to upload almost 2 years ago
ggml-model-q4_0.bin

4.92 GB
LFS

Adds the first quantization, type:2 q4_0 almost 2 years ago
ggml-model-q4_1.bin

5.91 GB
LFS

Adds the second quantization, type:3 q4_1 almost 2 years ago
ggml-model-q4_2.bin

4.92 GB
LFS

Adds the second quantization, type:5 q4_2 almost 2 years ago
ggml-model-q4_3.bin

5.91 GB
LFS

Adds the last quantization, type:6 q4_3, (LastCommit hgad type, not second, it was indeed the third almost 2 years ago