runanywhere
/

phi_tiny_moe_HNPU

Text Generation

Model card Files Files and versions

phi_tiny_moe_HNPU / v81

4.72 GB

Ctrl+K

Ctrl+K

3 contributors

History: 14 commits

sanmonga22's picture

Prune QHexRT HNPU bundle to runtime-minimum artifacts

b1b0f24 verified about 1 month ago

a_hi.bin

682 MB
xet

Upload v81/a_hi.bin with huggingface_hub about 2 months ago
a_lo.bin
Pickle imports
- No problematic imports detected
What is a pickle import?
682 MB
xet

Upload v81/a_lo.bin with huggingface_hub about 2 months ago
embed_f16.bin
Pickle imports
- No problematic imports detected
What is a pickle import?
263 MB
xet

Upload v81/embed_f16.bin with huggingface_hub about 2 months ago
experts_i8.bin
Pickle imports
- No problematic imports detected
What is a pickle import?
2.82 GB
xet

Upload v81/experts_i8.bin with huggingface_hub about 2 months ago
experts_scale.f32

10.2 MB
xet

Upload v81/experts_scale.f32 with huggingface_hub about 2 months ago
ffn2.bin

127 kB
xet

Upload v81/ffn2.bin with huggingface_hub about 2 months ago
lmhead_ar1.bin
Pickle imports
- No problematic imports detected
What is a pickle import?
263 MB
xet

Upload v81/lmhead_ar1.bin with huggingface_hub about 2 months ago
phimoe.json

1.32 kB
Prune QHexRT HNPU bundle to runtime-minimum artifacts about 1 month ago
tokenizer.json

1.84 MB
Upload v81/tokenizer.json with huggingface_hub about 2 months ago