Publish approved Variant MXQ

README.md

@@ -7,15 +7,65 @@ tags:
 base_model_relation: quantized
 ---
 
-<div align="center">
-  <a href="https://mobilint.com">
-    <img src="https://raw.githubusercontent.com/mobilint/.github/main/assets/Mobilint_Logo_Primary.png?raw=true" 
-         width="50%" 
-         alt="mobilint" />
-  </a>
-</div>
+# EfficientNet_V2_S_IMAGENET1K_V1
 
+`aries-rb/` holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/EfficientNet_V2_S_IMAGENET1K_V1). It was compiled by qbcompiler 1.4.0 in the image `mobilint/qbcompiler:1.4-cuda12.8.1-ubuntu22.04` (sha256:7910f1661605b82eb9616f6ac99fd6461dbb865dcadaa810cce22c638ceffd44) with `--inference-scheme single`, so it supports the core mode(s) `single` only.
 
-# About
-This repository provides a model compiled and optimized for Mobilint NPU hardware.  
-The model is packaged for deployment on Mobilint’s acceleration stack and is intended to be used within that environment.
+It was evaluated with qbruntime 1.5.0 in `async` inference mode on imagenet (50000 samples): top1_accuracy 0.8385, top5_accuracy 0.96778. Only the evaluated core mode was measured.
+
+SHA-256: `64f1572fa86f2067883aa98d676d8180a4f43a3f30705b9d21d8564669e7c66a` (24572635 bytes). Verify a download with `sha256sum <file>.mxq` and compare the digest with this value and with `aries-rb/metadata.json`.
+
+aries-rb/best_result.json contains legacy build values and is retained for mblt-vision-python compile defaults.
+The legacy aries/ directory was removed; mblt-model-zoo <= 2.12 must pin an older revision.
+
+```json
+{
+  "schema_version": 2,
+  "model": "EfficientNet_V2_S_IMAGENET1K_V1",
+  "variant": "c0923-gptaq",
+  "qbcompiler": "1.4.0",
+  "qbruntime": "1.5.0",
+  "compile": {
+    "image_tag": "1.4-cuda12.8.1-ubuntu22.04",
+    "image_digest": "sha256:7910f1661605b82eb9616f6ac99fd6461dbb865dcadaa810cce22c638ceffd44",
+    "inference_scheme": "single",
+    "device": "gpu"
+  },
+  "evaluation": {
+    "dataset": "imagenet",
+    "sample_count": 50000,
+    "primary": {
+      "top1_accuracy": 0.8385
+    },
+    "secondary": {
+      "top5_accuracy": 0.96778
+    },
+    "protocol": null,
+    "eval_data_identity": null,
+    "identity_audit": "absent",
+    "inference_mode": "async",
+    "image_tag": "1.4-cpu-ubuntu22.04",
+    "image_digest": "sha256:62b5bc714571dffd94fb561275767ca80d15337a433630a3ae7936305d531a7b"
+  },
+  "retention_percent": {
+    "top1_accuracy": 99.541763616506
+  },
+  "content_sha256": "f55b874c51490d6c3f3e9fdf34ad01edd7f29166795939cdc7b83c68c5fadf1a",
+  "attempt_id": "srcmodes16-efficientnet-v2-s-imagenet1k-v1-20261012t112800",
+  "superseded_attempt_ids": [],
+  "sha256": "64f1572fa86f2067883aa98d676d8180a4f43a3f30705b9d21d8564669e7c66a",
+  "format": "MXQv7",
+  "supported_modes": [
+    "single"
+  ],
+  "size": 24572635,
+  "ops_commits": {
+    "selection": "66d2f03be3d5af292a3bd707a630737ad5631488"
+  },
+  "arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/EfficientNet_V2_S_IMAGENET1K_V1",
+  "publication": {
+    "status": "public",
+    "reason": "approved"
+  }
+}
+```

aries-rb/efficientnet_v2_s_IMAGENET1K_V1.mxq

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff9128d6f69319837d28292165fbd66438f60bac04752ae3e3f5c281f304cb2
-size 26360440
+oid sha256:64f1572fa86f2067883aa98d676d8180a4f43a3f30705b9d21d8564669e7c66a
+size 24572635

aries-rb/metadata.json

@@ -0,0 +1,49 @@
+{
+  "schema_version": 2,
+  "model": "EfficientNet_V2_S_IMAGENET1K_V1",
+  "variant": "c0923-gptaq",
+  "qbcompiler": "1.4.0",
+  "qbruntime": "1.5.0",
+  "compile": {
+    "image_tag": "1.4-cuda12.8.1-ubuntu22.04",
+    "image_digest": "sha256:7910f1661605b82eb9616f6ac99fd6461dbb865dcadaa810cce22c638ceffd44",
+    "inference_scheme": "single",
+    "device": "gpu"
+  },
+  "evaluation": {
+    "dataset": "imagenet",
+    "sample_count": 50000,
+    "primary": {
+      "top1_accuracy": 0.8385
+    },
+    "secondary": {
+      "top5_accuracy": 0.96778
+    },
+    "protocol": null,
+    "eval_data_identity": null,
+    "identity_audit": "absent",
+    "inference_mode": "async",
+    "image_tag": "1.4-cpu-ubuntu22.04",
+    "image_digest": "sha256:62b5bc714571dffd94fb561275767ca80d15337a433630a3ae7936305d531a7b"
+  },
+  "retention_percent": {
+    "top1_accuracy": 99.541763616506
+  },
+  "content_sha256": "f55b874c51490d6c3f3e9fdf34ad01edd7f29166795939cdc7b83c68c5fadf1a",
+  "attempt_id": "srcmodes16-efficientnet-v2-s-imagenet1k-v1-20261012t112800",
+  "superseded_attempt_ids": [],
+  "sha256": "64f1572fa86f2067883aa98d676d8180a4f43a3f30705b9d21d8564669e7c66a",
+  "format": "MXQv7",
+  "supported_modes": [
+    "single"
+  ],
+  "size": 24572635,
+  "ops_commits": {
+    "selection": "66d2f03be3d5af292a3bd707a630737ad5631488"
+  },
+  "arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/image_classification/EfficientNet_V2_S_IMAGENET1K_V1",
+  "publication": {
+    "status": "public",
+    "reason": "approved"
+  }
+}

aries/best_result.json

@@ -1 +0,0 @@
-{"acc": 0.77814, "timestamp": 1777149860, "checkpoint_dir_name": null, "done": true, "training_iteration": 1, "trial_id": "8d547d45", "date": "2026-04-26_05-44-20", "time_this_iter_s": 1775.4700591564178, "time_total_s": 1775.4700591564178, "pid": 1529207, "hostname": "ae30e054f296", "node_ip": "172.17.0.3", "config": {"percentile": 0.0017356731757517678, "topk": 0.023524980211262154}, "time_since_restore": 1775.4700591564178, "iterations_since_restore": 1, "experiment_tag": "20_percentile=0.0017,topk=0.0235"}

aries/efficientnet_v2_s_IMAGENET1K_V1.mxq

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ff9128d6f69319837d28292165fbd66438f60bac04752ae3e3f5c281f304cb2
-size 26360440