[docs]: use the FastH3-QAD-v2 name

Update the model card title and self-reference after the repository rename.

README.md

@@ -3,9 +3,9 @@ license: other
 base_model: FastVideo/FastVideo-FastH3-8-Step-V2
 tags: [video-generation, text-to-video, audio, fastvideo, nvfp4, qad]
 ---
-# FastH3 V2.1, 8-step, NVFP4 for one GPU (QAD)
+# FastH3-QAD-v2 (V2.1), 8-step, NVFP4 for one GPU
 
-FastH3 V2.1 is an 8-step video-and-audio model with NVFP4 weights, trained with **quantization-aware distillation
+FastH3-QAD-v2 is an 8-step video-and-audio model with NVFP4 weights, trained with **quantization-aware distillation
 (QAD)**. It runs on one Blackwell GPU (RTX 5090, RTX PRO 6000) or a DGX Spark.
 
 - **Transformer:** 50 blocks, NVFP4 W4A4 on all attention q/k/v/out and MLP linears, plus the sparse-attention
@@ -42,7 +42,7 @@ import os
 from huggingface_hub import hf_hub_download
 
 os.environ["FASTVIDEO_H3_ADALN_TABLE"] = hf_hub_download(
-    "FastVideo/FastVideo-FastH3-8-Step-V2.1-NVFP4-Consumer", "transformer/adaln_tables.pt")
+    "FastVideo/FastH3-QAD-v2", "transformer/adaln_tables.pt")
 ```
 
 The table covers only the shipped schedule (`fastvideo_inference.json`); FastVideo raises an error for other timesteps.