Add static INT8 channelwise ResNet101 model

README.md

@@ -48,6 +48,20 @@ acc@1 (on ImageNet-1K): 77.374%
 acc@5 (on ImageNet-1K): 93.546%    
 num_params: 44,549,160 
 
+## Available model files
+
+| File | Description |
+| --- | --- |
+| `resnet101.tflite` | Full precision LiteRT/TFLite model. |
+| `resnet101_dynamic_wi8_afp32.tflite` | Dynamic weight-only INT8 model with FP32 activations. |
+| `resnet101_int8_channelwise.tflite` | Static INT8 model with channelwise INT8 weights and asymmetric INT8 activations. |
+
+## Quantization
+
+`resnet101_int8_channelwise.tflite` was produced with the `STATIC_WI8_AI8` quantization recipe. Weights are signed INT8 and use symmetric channelwise quantization for weight tensors. Activations are signed INT8 with asymmetric quantization parameters.
+
+The INT8 channelwise artifact keeps standard LiteRT/TFLite model structure before AOT compilation. Local LiteRT compiler checks fully delegated this artifact for Qualcomm NPU targets. MediaTek NPU compiler checks produced partial delegation for this channelwise artifact, with a small number of Conv2D ops left outside the NPU partition.
+
 ## Intended uses & limitations
 
 The model files were converted from pretrained weights from PyTorch Vision. The models may have their own licenses or terms and conditions derived from PyTorch Vision and the dataset used for training. It is your responsibility to determine whether you have permission to use the models for your use case.
@@ -140,4 +154,4 @@ author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
 booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition}, pages={770--778}, 
 year={2016} 
 }
-```
+```

resnet101_int8_channelwise.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97861fd0fae2a40706027827d66c180668370773d17722a9aef83e342cbd77f
+size 46006576