1 contributor

History: 86 commits

jartine

Quantize BF16 with llamafile-0.8.9

27622a0 verified 5 months ago

.gitattributes

2.72 kB

Quantize Phi-3-mini-4k-instruct with llamafile-0.8.1 BF16 7 months ago
LICENSE

4.81 kB

Update README.md 7 months ago
Phi-3-mini-4k-instruct.BF16.llamafile

7.67 GB
LFS

Quantize BF16 with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.F16.llamafile

7.67 GB
LFS

Quantize F16 with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q2_K.llamafile

1.45 GB
LFS

Quantize Q2_K with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q3_K_L.llamafile

2.12 GB
LFS

Quantize Q3_K_L with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q3_K_M.llamafile

1.99 GB
LFS

Quantize Q3_K_M with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q3_K_S.llamafile

1.71 GB
LFS

Quantize Q3_K_S with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q4_0.llamafile

2.21 GB
LFS

Quantize Q4_0 with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q4_1.llamafile

2.44 GB
LFS

Quantize Q4_1 with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q4_K_M.llamafile

2.42 GB
LFS

Quantize Q4_K_M with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q4_K_S.llamafile

2.22 GB
LFS

Quantize Q4_K_S with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q5_0.llamafile

2.67 GB
LFS

Quantize Q5_0 with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q5_1.llamafile

2.9 GB
LFS

Quantize Q5_1 with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q5_K_M.llamafile

2.85 GB
LFS

Quantize Q5_K_M with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q5_K_S.llamafile

2.67 GB
LFS

Quantize Q5_K_S with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q6_K.llamafile

3.17 GB
LFS

Quantize Q6_K with llamafile-0.8.9 5 months ago
Phi-3-mini-4k-instruct.Q8_0.llamafile

4.09 GB
LFS

Quantize Q8_0 with llamafile-0.8.9 5 months ago
README.md

21.7 kB

Update README.md 7 months ago