finalize pinned NVFP4A16 checkpoint metadata

README.md

@@ -33,7 +33,7 @@ Verified on shard 49, expert 0, real K3 w1/w2/w3 weights: all packed bytes are i
 - Lossless over-span policy: `fail; never silently requantize`
 - Tensor data size: 1.497 TiB
 - Size change versus source tensor data: +5.45%
-- Planned companion artifact (not yet published): `GrEarl/Kimi-K3-NVFP4A16-Requantized`
+- Companion artifact: [`GrEarl/Kimi-K3-NVFP4A16-Requantized`](https://huggingface.co/GrEarl/Kimi-K3-NVFP4A16-Requantized)
 
 This is **NVFP4A16**, not calibrated W4A4 NVFP4. Kimi K3 was trained
 with MXFP8 activations; FP4 activation quantization would require a separate