Sync model repo (text/metadata)
Browse files
README.md
CHANGED
|
@@ -176,6 +176,7 @@ This model is intended for developers evaluating image classification workloads
|
|
| 176 |
## Additional notes
|
| 177 |
|
| 178 |
Patch embeddings are kept in FP32 on this export. The model's quantization spec excludes this layer to avoid a static-transpose graph pattern that the XNNPACK delegate cannot compile on the ExecuTorch export; that same declarative skip list is shared across backends, so it also applies to this LiteRT export even though LiteRT itself has no such compile constraint. Latency and memory were measured with the model pinned to a single CPU core on the vivo X300.
|
|
|
|
| 179 |
- Sample input: `sample_input.jpg` is derived from [Samoyed on Beach](https://commons.wikimedia.org/wiki/File:Samoyed_on_Beach.jpg) by Appleinfl, via Wikimedia Commons (public domain).
|
| 180 |
|
| 181 |
## About this version
|
|
|
|
| 176 |
## Additional notes
|
| 177 |
|
| 178 |
Patch embeddings are kept in FP32 on this export. The model's quantization spec excludes this layer to avoid a static-transpose graph pattern that the XNNPACK delegate cannot compile on the ExecuTorch export; that same declarative skip list is shared across backends, so it also applies to this LiteRT export even though LiteRT itself has no such compile constraint. Latency and memory were measured with the model pinned to a single CPU core on the vivo X300.
|
| 179 |
+
|
| 180 |
- Sample input: `sample_input.jpg` is derived from [Samoyed on Beach](https://commons.wikimedia.org/wiki/File:Samoyed_on_Beach.jpg) by Appleinfl, via Wikimedia Commons (public domain).
|
| 181 |
|
| 182 |
## About this version
|