1 contributor

History: 160 commits

jartine

Quantize F16 with llamafile-0.8.12

cfcb20d verified 3 months ago

.gitattributes

3.47 kB

Quantize F16 with llamafile-0.8.12 3 months ago
README.md

20.8 kB

Update README.md 6 months ago
config.json

31 Bytes

Add config.json to repo 10 months ago
mixtral-8x7b-instruct-v0.1.BF16.llamafile.cat0
50 GB
LFS

Quantize BF16 with llamafile-0.8.9 4 months ago
mixtral-8x7b-instruct-v0.1.BF16.llamafile.cat1
43.4 GB
LFS

Quantize BF16 with llamafile-0.8.9 4 months ago
mixtral-8x7b-instruct-v0.1.F16.cat0.llamafile
50 GB
LFS

Quantize F16 with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.F16.cat1.llamafile
43.4 GB
LFS

Quantize F16 with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.F16.llamafile.cat0
50 GB
LFS

Quantize F16 with llamafile-0.8.9 4 months ago
mixtral-8x7b-instruct-v0.1.F16.llamafile.cat1
43.4 GB
LFS

Quantize F16 with llamafile-0.8.9 4 months ago
mixtral-8x7b-instruct-v0.1.Q2_K.llamafile
17.3 GB
LFS

Quantize Q2_K with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q3_K_M.llamafile
22.6 GB
LFS

Quantize Q3_K_M with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q3_K_S.llamafile
20.5 GB
LFS

Quantize Q3_K_S with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q4_0.llamafile
26.5 GB
LFS

Quantize Q4_0 with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q4_1.llamafile
29.4 GB
LFS

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.7.3 Q4_1 6 months ago
mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile
28.5 GB
LFS

Quantize Q4_K_M with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q5_0.llamafile
32.3 GB
LFS

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.7 Q5_0 7 months ago
mixtral-8x7b-instruct-v0.1.Q5_K_M.llamafile
33.3 GB
LFS

Quantize Q5_K_M with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q5_K_S.llamafile
32.3 GB
LFS

Quantize Q5_K_S with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q6_K.llamafile
38.4 GB
LFS

Quantize Q6_K with llamafile-0.8.12 3 months ago
mixtral-8x7b-instruct-v0.1.Q8_0.llamafile
49.7 GB
LFS

Quantize Q8_0 with llamafile-0.8.12 3 months ago