Upload index.html with huggingface_hub
Browse files- index.html +1 -1
index.html
CHANGED
|
@@ -387,7 +387,7 @@
|
|
| 387 |
</table>
|
| 388 |
|
| 389 |
<p id="platform-notes" class="footnote">
|
| 390 |
-
✓ indicates a compiled model artifact is published in the corresponding repo. <sup>[1]</sup> Some
|
| 391 |
</p>
|
| 392 |
|
| 393 |
<!-- Overview: All families comparison -->
|
|
|
|
| 387 |
</table>
|
| 388 |
|
| 389 |
<p id="platform-notes" class="footnote">
|
| 390 |
+
✓ indicates a compiled model artifact is published in the corresponding repo. <sup>[1]</sup> Some (size, platform) combinations are work in progress and are not yet showing a number in the per-repo model card's <em>On-target validation results</em> table. Two reasons cover most cases: <em>timing</em> — larger sizes on slower NPUs are not yet a validation priority and will roll in as bandwidth allows; and <em>accuracy or performance investigations</em> — for example, YOLO11 and YOLO26 on the i.MX 95 Neutron currently show a quantization regression that we are tracking with NXP. In every case the underlying Studio validation session (<code>v-XXXX</code>) remains linked in the model card so its current status can be inspected.
|
| 391 |
</p>
|
| 392 |
|
| 393 |
<!-- Overview: All families comparison -->
|