Sync model repo (text/metadata)

README.md

@@ -1,6 +1,5 @@
 ---
 library_name: executorch
-display_name: DeiT-Tiny INT8 — ExecuTorch + XNNPACK
 base_model: facebook/deit-tiny-patch16-224
 base_model_relation: quantized
 license: apache-2.0

benchmarks/README.md

@@ -1,39 +0,0 @@
-# Benchmarks
-
-Machine-readable measurement records for this model, conforming to
-the AI Portal model schema
-v1.0.0 (`task: vision-classification`).
-
-These complement — they don't replace — the eval block in the model
-card. The card carries the headline numbers in human-readable form;
-these YAMLs carry the same data with full context (target hardware,
-runtime config, dataset slice, benchmark parameters) so downstream
-tooling can ingest them programmatically.
-
-## Files
-
-- `deit-tiny-raspberrypi5-int8.yaml` — INT8 measurements on
-  Raspberry Pi 5 via ExecuTorch + XNNPACK + KleidiAI.
-- `deit-tiny-raspberrypi5-fp32.yaml` — FP32 baseline on the same
-  hardware/runtime, for comparison.
-
-## Reading these
-
-Each record has three top-level sections:
-
-- `context.{model,target,runtime,dataset,benchmark}` — everything
-  needed to reproduce the measurement.
-- `performance` — latency (p50/p90), memory (peak/average), FPS,
-  delegation %.
-- `accuracy` — Top-1 / Top-5 percentages.
-
-The two records share `context.{target,runtime,dataset,benchmark}`;
-the disambiguator is `weight_dtype` (and, once published under an
-`Arm/*` slug, `model.id`).
-
-## Provenance
-
-Copied field-for-field from the producer delivery
-`deit_raspberry_executorch_v2`: the INT8 record from
-`huggingface/metadata.yaml`, the FP32 baseline from
-`huggingface/baseline_metadata.yaml`.