Hugging Face's logo

mlboydaisuke
/
granite-4.0-h-CoreAI

coreai
coreai-aimodel
apple
aimodel
on-device
granite
mamba2
apple-silicon
macos
ios
hybrid
granite-4.0-h
tokens-per-second
m4-max
iphone-17-pro
Model card Files
xet
 Community
granite-4.0-h-CoreAI / gpu-pipelined

Commit History

  1. granite_4_0_h_350m_decode_fp16: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py

    mlboydaisuke
    Verified signature
    f361cfc

  1. Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle

    mlboydaisuke
    Verified signature
    e0c884d

  2. Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle

    mlboydaisuke
    Verified signature
    a3cdae0

  1. Upload folder using huggingface_hub

    mlboydaisuke
    Verified signature
    0fe4178

  2. add granite_4_0_h_350m_decode_fp16 LanguageBundle

    mlboydaisuke
    Verified signature
    3247cc6

  3. add granite_4_0_h_1b_decode_int8lin LanguageBundle

    mlboydaisuke
    Verified signature
    30fccc0