Commit History
-
Update validated TorchVision exports and compatibility documentation
Verified signaturePublish the reviewed model files and current CPU/GPU/NPU compatibility table.3b82802
-
Remove inaccurate MobileNetV3 Small static INT8 model
Verified signatureWithdraw the static INT8 artifact after accuracy validation. Document the activation quantization issue, ongoing work, and MobileNetV3 Large recommendation.16a1a16
-
Replace the dynamic int8 file with a weight-only int8 file (#2)
- Replace the dynamic int8 file with a weight-only int8 file (7e59d91732c403b208b5e422e872ba6777911c5a) Co-authored-by: Majima <mlboydaisuke@users.noreply.huggingface.co>919ae75
-
Update model card
Verified signature13a1cd8
-
Add static INT8 channelwise MobileNetV3-small model
Verified signature77f1385
-
Upload mobilenet_v3_small_Google_Tensor_G5_apply_plugin.tflite with huggingface_hub
Verified signaturee988dea
-
Restore previous model card
Verified signaturef10056c -
Upload GPU-compatible LiteRT artifacts
Verified signaturee10661f
-
Update README: Add model card metadata, ImageNet-1k metrics, and LiteRT usage example (#1)
- Update README: Add model card metadata, ImageNet-1k metrics, and LiteRT usage example (02ae61262ececac41ec712c277e8e368443d8986) - Update README: Add model card metadata, ImageNet-1k metrics, and LiteRT usage example (74311df5b13b6c4f7fc55bc74eecde3c2f3585fe) - Update README (361950880b566666ba1923df7b1261e7712f4b1b) Co-authored-by: Akash Verma <akashvverma1995@users.noreply.huggingface.co>0a00965
-
Update metadata with huggingface_hub
Verified signature83721b0 -
Upload folder using huggingface_hub
Verified signature62fcb6b -
initial commit
Verified signature1b13ea4