Update success-stories.md (#15309)

Update unsloth QAT story to use qwen example, which has more details
than llama example.

Author: metascroy

docs/source/success-stories.md

@@ -106,7 +106,7 @@ PyTorch-native quantization and optimization library for preparing efficient mod
 
 Optimize LLM fine-tuning with faster training and reduced VRAM usage, then deploy efficiently with ExecuTorch.
 
-[Example Model →](https://huggingface.co/metascroy/Llama-3.2-1B-Instruct-int8-int4)
+[Example Model →](https://huggingface.co/metascroy/Qwen3-4B-int8-int4-unsloth)
 :::
 
 ::::
@@ -125,4 +125,4 @@ Optimize LLM fine-tuning with faster training and reduced VRAM usage, then deplo
 
 - **Demo title** - Brief description of the demo [Try →](#)
 
-*Want to showcase your demo? [Submit here →](https://github.com/pytorch/executorch/issues)*
+*Want to showcase your demo? [Submit here →](https://github.com/pytorch/executorch/issues)*