runanywhere
/

phi_tiny_moe_HNPU

Text Generation

Model card Files Files and versions

phi_tiny_moe_HNPU

10.8 GB

Ctrl+K

Ctrl+K

3 contributors

History: 53 commits

sanmonga22's picture

remove v75 bundle: not Plane-B-validated (Plane B OOM (5.4GB MoE > app ceiling))

80f24b2 verified 28 days ago

v79
Prune QHexRT HNPU bundle to runtime-minimum artifacts 29 days ago
v81
Prune QHexRT HNPU bundle to runtime-minimum artifacts 29 days ago
.gitattributes

1.75 kB
Add v75 (SM8650) bundle: decode-only MoE, device-validated (Paris/4 correct) 29 days ago
README.md

565 Bytes
Add HNPU arch tags to sanitized model card 30 days ago