Fix: cross-reference links point to HuggingFace

README.md

@@ -20,7 +20,7 @@ pipeline_tag: text-generation
 
 > **Note on training data**: Due to limited compute resources, both pretraining and SFT used only **small subsets** of their respective datasets (pretrain ~1.4B of ~10B tokens; SFT ~6.5K steps of ~3.5M samples). Despite this minimal data budget, the model demonstrates coherent Chinese dialogue — validating that pure SNN architectures can learn language from scratch. We plan to scale training with more data and compute in future work.
 
-For the pretrained base model, see [NeuronSpark-0.9B](https://modelscope.cn/models/Brain2nd/NeuronSpark-0.9B).
+For the pretrained base model, see [NeuronSpark-0.9B](https://huggingface.co/Brain2nd/NeuronSpark-0.9B).
 
 ## Model Details