Classify compiled quantized runtime package and clarify upstream weight provenance

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 base_model: amd/Qwen3.8-27B-Quark-Qronos-INT4-W4A16
+base_model_relation: quantized
 library_name: paiton
 pipeline_tag: text-generation
 inference: false
@@ -76,6 +77,10 @@ curl --fail http://127.0.0.1:8000/v1/chat/completions \
 
 ## Model and execution details
 
+The Hub quantization relationship identifies this compiled runtime package
+with its upstream quantized checkpoint. It does not indicate that this
+repository publishes a new set of quantized weights.
+
 - Original repository: [amd/Qwen3.8-27B-Quark-Qronos-INT4-W4A16](https://huggingface.co/amd/Qwen3.8-27B-Quark-Qronos-INT4-W4A16).
 - Pinned weight revision: `649ca9d47a7de5364c6fcccc0c1b4f6e542e15e2`.
 - Execution format: Qronos INT4 checkpoint; fitted INT3 MLP decode shadows and W4 LM head.

SHA256SUMS

@@ -3,7 +3,7 @@ c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4  LICENSE
 20f3b83dfda01bd18d285e0edbb9d044be6dde04cdf76a1ec18d9fc7127936bf  LICENSES/Composable-Kernel-MIT.txt
 92640fb97222fd0a698ff28ce0c3782c172623f8d6c609b557636a80f28fb946  LICENSES/Triton-MIT.txt
 1350bfbef13ce4d3d3bdaa2f1fc4b1d1117d846732a2a62f891a67f3d5356d0d  LICENSES/flash-linear-attention-MIT.txt
-0e608e3d8e72304126a1b1b2ed8439e868fb03c256b555828d63c245fe9e3c6b  README.md
+111d1b024f770668fd3516adfab3f4c49faaaabf0559a3067bcf85ebbc0cdbbe  README.md
 f94ffb025a87555d6ed23683699685d841d171ff64926ce569b01aa64448096d  THIRD_PARTY_NOTICES.md
 18bd30d71285356472f7482ed7ec45dbba6f733ad902f0059ad3e1364edb2f23  overlay/Qwen3.8-27B-Quark-Qronos-INT4-W4A16_gfx1201_tp1_mt8192_ctx8192.manifest.json
 be534b72dc47094e1d067594e8642174909f7ab223676daa29d0f9a95c5b55b3  overlay/Qwen3.8-27B-Quark-Qronos-INT4-W4A16_gfx1201_tp1_mt8192_ctx8192.so