Sync model repo (text/metadata)

README.md

@@ -21,7 +21,7 @@ DeiT-Tiny optimized with INT8 post-training quantization for most eligible opera
 
 This repository contains an Arm-optimized version of facebook/deit-tiny-patch16-224 for image classification. The model is provided in ExecuTorch `.pte` format, targeting Edge Linux systems.
 
-This version is intended to demonstrate efficient inference on Arm-based platforms while preserving the original model's intended behavior. Arm has evaluated this model on ImageNet-1k and measured performance on Raspberry Pi 5.
+This version is intended to demonstrate efficient inference on Arm-based platforms while preserving the original model's intended behavior. Arm has evaluated this model on ImageNet-1k and measured performance on a representative evaluation target.
 
 **Key results**
 
@@ -29,7 +29,7 @@ This version is intended to demonstrate efficient inference on Arm-based platfor
 |---|---|
 | Model format | ExecuTorch `.pte` |
 | Target device class | Edge Linux |
-| Reference device | Raspberry Pi 5 (Cortex-A76, linux Raspberry Pi OS 64-bit, based on Debian 13 "Trixie") |
+| Reference device | Raspberry Pi 5 (Cortex-A76, Linux Raspberry Pi OS 64-bit, based on Debian 13 "Trixie") |
 | Primary performance result | 26.40 ms p50 latency (37.88 FPS) |
 | Accuracy result | Top-1 71.36%, Top-5 90.74% |
 | Size / memory result | 6.62 MB (3.32x smaller than the FP32 baseline) |
@@ -65,7 +65,7 @@ Performance was measured on the reference configuration below. Results are inten
 |---|---|
 | Device / platform | Raspberry Pi 5 |
 | CPU / accelerator | Cortex-A76 (arm64, 4 cores, 2.4 GHz) |
-| OS | linux, Raspberry Pi OS 64-bit, based on Debian 13 "Trixie" |
+| OS | Linux, Raspberry Pi OS 64-bit, based on Debian 13 "Trixie" |
 | Runtime | ExecuTorch 1.1.0 |
 | Backend / delegate | XNNPACK, KleidiAI |
 | Batch size | 1 |