Fixed broken stuff in the model card

README.md

@@ -26,11 +26,34 @@ extra_gated_description: |
 extra_gated_button_content: Request access
 ---
 
-<p align="center">
-  <a href="https://embedl.com">
-    <img src="https://huggingface.co/datasets/embedl/documentation-images/resolve/main/embedl_banner.svg" alt="Embedl" width="240">
-  </a>
-</p>
+<!-- embedl-banner:start -->
+<style>
+.embedl-btn-primary { transition: background 160ms ease, box-shadow 160ms ease; }
+.embedl-btn-primary:hover { background: #4FDCE4 !important; box-shadow: 0 8px 22px rgba(45,212,221,0.45) !important; }
+.embedl-btn-secondary { transition: background 160ms ease; }
+.embedl-btn-secondary:hover { background: rgba(45,212,221,0.15) !important; }
+.embedl-headline { font-size: clamp(11px, 2.15vw, 15px) !important; }
+.embedl-btn-primary, .embedl-btn-secondary {
+  font-size: clamp(11px, 1.65vw, 13px) !important;
+  padding: clamp(6px, 1.1vw, 9px) clamp(10px, 1.6vw, 14px) !important;
+}
+</style>
+<div style="background:radial-gradient(600px 220px at 0% 50%,rgba(45,212,221,0.22) 0%,rgba(45,212,221,0) 60%),radial-gradient(400px 180px at 100% 100%,rgba(45,212,221,0.10) 0%,rgba(45,212,221,0) 55%),linear-gradient(135deg,#0B1626 0%,#142338 100%);border:1px solid rgba(45,212,221,0.28);border-radius:12px;padding:22px 24px;margin:0 0 24px 0;color:#F2F6FA;box-shadow:0 4px 16px rgba(11,22,38,0.18);overflow:hidden;box-sizing:border-box;max-width:100%;">
+  <table style="width:100%;border-collapse:collapse;border:0;background:transparent;">
+    <tr style="background:transparent;">
+      <td style="vertical-align:middle;border:0;padding:0;background:transparent;">
+        <div style="display:inline-block;font-size:10px;letter-spacing:0.08em;text-transform:uppercase;font-weight:700;color:#2DD4DD;background:rgba(45,212,221,0.15);border:1px solid rgba(45,212,221,0.35);padding:4px 10px;border-radius:999px;margin-bottom:10px;white-space:nowrap;">Optimized by Embedl</div>
+        <div class="embedl-headline" style="font-size:15px;font-weight:700;line-height:1.35;color:#F2F6FA;margin-bottom:4px;">Need to <span style="color:#2DD4DD;white-space:nowrap;">fine-tune</span>, hit <span style="color:#2DD4DD;white-space:nowrap;">performance targets</span>, or deploy on <span style="color:#2DD4DD;white-space:nowrap;">specific hardware</span>?</div>
+        <div style="font-size:13px;color:#9BA7B5;">We've got you covered.</div>
+      </td>
+      <td width="1%" style="vertical-align:middle;border:0;padding:0 0 0 18px;white-space:nowrap;text-align:right;background:transparent;">
+        <a href="https://www.embedl.com/models" class="embedl-btn-secondary" style="display:inline-block;font-size:13px;font-weight:600;padding:9px 14px;border-radius:6px;border:1px solid #2DD4DD;color:#2DD4DD;text-decoration:none;margin-right:8px;">Learn more</a>
+        <a href="https://www.embedl.com/contact" class="embedl-btn-primary" style="display:inline-block;font-size:13px;font-weight:600;padding:9px 14px;border-radius:6px;border:1px solid #2DD4DD;background:#2DD4DD;color:#0B1626;text-decoration:none;box-shadow:0 6px 18px rgba(45,212,221,0.28);">Get in touch →</a>
+      </td>
+    </tr>
+  </table>
+</div>
+<!-- embedl-banner:end -->
 
 # Embedl Chronos-2 (Quantized for TensorRT)
 
@@ -42,14 +65,24 @@ low-latency NVIDIA TensorRT inference on edge GPUs. Two
 static-context variants ship: **ctx=512** for short-history
 forecasting and **ctx=2048** for long-history use cases.
 
+## Upstream Model
+
+<a href="https://hfviewer.com/amazon/chronos-2?utm_source=huggingface&amp;utm_medium=embedded_model_card&amp;utm_campaign=amazon__chronos-2_card" target="_blank" rel="noopener">
+  <img
+    src="https://hfviewer.com/api/card.svg?source=amazon%2Fchronos-2&amp;v=20260501clipcard"
+    alt="Open amazon/chronos-2 in hfviewer"
+    width="100%"
+  />
+</a>
+
 ## Highlights
 
 - **Per-tensor INT8** activations + **per-channel INT8** weights via
   embedl-deploy's PTQ flow on top of TensorRT's fused MHA kernel.
   No QAT or distillation needed.
 - **Drop-in replacement** for `amazon/chronos-2` inference: same
-  `(context, group_ids) → quantile_preds` signature; 21-quantile
-  output grid (0.01..0.99 step 0.05).
+  `(context, group_ids) → quantile_preds` signature; 21 evenly
+  spaced quantile levels with the median at index 10.
 - **Validated** on the [GIFT-Eval](https://huggingface.co/datasets/Salesforce/GiftEval)
   benchmark across 125 task configurations. See Accuracy below.
 - **Two ctx variants** so you can pick the latency/history-window
@@ -86,7 +119,7 @@ Latency measured with TensorRT + `trtexec`, GPU compute time only
 (`--noDataTransfers`), CUDA Graph + Spin Wait enabled, clocks locked
 (`nvpmodel -m 0 && jetson_clocks` on Jetson).
 
-### Jetson Orin Nano Super
+### Jetson AGX Orin (MAXN)
 
 #### ctx=512
 
@@ -147,20 +180,6 @@ forecasts (`solar/10T/{medium,long}`). The full per-task CSVs
 ship with the artifacts; check them before deploying to a domain
 that resembles those outliers.
 
-## How This Was Built
-
-1. **Trace.** `torch.export` on `amazon/chronos-2` at static
-   ctx={512, 2048}, `num_output_patches=64` (1024-step horizon).
-2. **Transform.** embedl-deploy's TensorRT pattern set recomposes
-   chronos-2's manual SDPA + RoPE into fused INT8-ready modules.
-3. **Quantize (PTQ).** Per-tensor symmetric INT8 activations +
-   per-channel INT8 weights. Calibrated on a 1327-window cohort
-   drawn from 28 diverse GIFT-Eval **training** splits (no eval-set
-   leakage).
-4. **Export.** ONNX opset 20 + onnxslim + onnxsim simplification,
-   with Bool→Float casts inserted before Einsum nodes for TRT 10.x
-   compatibility.
-
 ## Creating Your Own Optimized Models
 
 This artifact was produced with
@@ -183,3 +202,24 @@ We offer engineering support for on-prem/edge deployments and partner
 co-marketing opportunities. Reach out at
 [contact@embedl.com](mailto:contact@embedl.com), or open an issue on
 [GitHub](https://github.com/embedl/embedl-deploy).
+
+<!-- embedl-discord-banner:start -->
+<style>
+.embedl-discord-btn { transition: background 160ms ease, box-shadow 160ms ease; }
+.embedl-discord-btn:hover { background: #6C77F5 !important; box-shadow: 0 8px 22px rgba(88,101,242,0.55) !important; }
+</style>
+<div style="background:radial-gradient(600px 220px at 0% 50%,rgba(88,101,242,0.22) 0%,rgba(88,101,242,0) 60%),radial-gradient(400px 180px at 100% 100%,rgba(88,101,242,0.10) 0%,rgba(88,101,242,0) 55%),linear-gradient(135deg,#0B1626 0%,#142338 100%);border:1px solid rgba(88,101,242,0.35);border-radius:12px;padding:22px 24px;margin:24px 0 0 0;color:#F2F6FA;box-shadow:0 4px 16px rgba(11,22,38,0.18);overflow:hidden;box-sizing:border-box;max-width:100%;">
+  <table style="width:100%;border-collapse:collapse;border:0;background:transparent;">
+    <tr style="background:transparent;">
+      <td style="vertical-align:middle;border:0;padding:0;background:transparent;">
+        <div style="display:inline-block;font-size:10px;letter-spacing:0.08em;text-transform:uppercase;font-weight:700;color:#A5B4FC;background:rgba(88,101,242,0.18);border:1px solid rgba(88,101,242,0.45);padding:4px 10px;border-radius:999px;margin-bottom:10px;white-space:nowrap;">Community &amp; support</div>
+        <div style="font-size:15px;font-weight:700;line-height:1.35;color:#F2F6FA;margin-bottom:4px;">Need help with this model? Chat with the Embedl team and other engineers on <span style="color:#A5B4FC;white-space:nowrap;">Discord</span>.</div>
+        <div style="font-size:13px;color:#9BA7B5;">Quantization gotchas, hardware questions, fine-tuning tips — bring them all.</div>
+      </td>
+      <td width="1%" style="vertical-align:middle;border:0;padding:0 0 0 18px;white-space:nowrap;text-align:right;background:transparent;">
+        <a href="https://discord.gg/MTbMWdKqE" class="embedl-discord-btn" style="display:inline-block;font-size:13px;font-weight:600;padding:9px 14px;border-radius:6px;border:1px solid #5865F2;background:#5865F2;color:#FFFFFF;text-decoration:none;box-shadow:0 6px 18px rgba(88,101,242,0.35);">Join our Discord →</a>
+      </td>
+    </tr>
+  </table>
+</div>
+<!-- embedl-discord-banner:end -->

infer_trt.py

@@ -22,9 +22,8 @@ from pathlib import Path
 import numpy as np
 import onnxruntime as ort
 
-# Native output grid emitted by the model: 21 quantiles spaced 0.01..0.99
-# step 0.05; the index of the median (q=0.5) is element 10.
-QUANTILE_LEVELS = [round(0.01 + 0.05 * i, 2) for i in range(21)]
+# chronos-2 emits 21 evenly spaced quantile levels along axis 1 of
+# the output. The median (q=0.5) is element 10.
 MEDIAN_IDX = 10
 NUM_OUTPUT_PATCHES = 64       # baked into the ONNX
 OUTPUT_PATCH_SIZE = 16        # baked into the ONNX