TheBloke
/

LLaMa-13B-GGML

Model card Files Files and versions

59.7 GB

Ctrl+K

Ctrl+K

2 contributors

History: 22 commits

TheBloke's picture

Upload new k-quant GGML quantised models.

8f93fd0 almost 3 years ago

.gitattributes

1.48 kB
initial commit almost 3 years ago
README.md

2.96 kB
Update README.md almost 3 years ago
config.json

27 Bytes
Create config.json (#1) almost 3 years ago
llama-13b.ggmlv3.q2_K.bin

5.43 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
llama-13b.ggmlv3.q3_K_M.bin

6.25 GB
xet

Upload new k-quant GGML quantised models. almost 3 years ago
llama-13b.ggmlv3.q4_0.bin

7.32 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
llama-13b.ggmlv3.q4_1.bin

8.14 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
llama-13b.ggmlv3.q5_0.bin

8.95 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
llama-13b.ggmlv3.q5_1.bin

9.76 GB
xet

New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48 almost 3 years ago
llama-13b.ggmlv3.q8_0.bin

13.8 GB
xet

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