Update README.md

README.md

@@ -1,9 +1,17 @@
 ---
 license: mit
 inference: false
+tags:
+- music
 ---
 
-# Introduction
+# Introduction to our series work
+
+Our MAP pre-trained music model family:
+- a pre-trained MIR model [music2vec](https://huggingface.co/m-a-p/music2vec-v1) before, which shares similar model structure but has weaker performance.
+- a model trained with open-source music dataset [MERT-v0-public](https://huggingface.co/m-a-p/MERT-v0-public)
+
+# Introduction to this model
 
 **MERT-v0** is a completely unsupervised model trained on 1000 hour music audios. 
 Its architecture is similar to the [HuBERT model](https://huggingface.co/docs/transformers/model_doc/hubert), but it has been specifically designed for music through the use of specialized pre-training strategies. 
@@ -11,7 +19,6 @@ It is SOTA-comparable on multiple MIR tasks even under probing settings, while k
 It outperforms Jukebox representation on GTZAN (genre classification) and GiantSteps (key classification) datasets.
 Larger models trained with more data are on the way.
 
-Noted: we also release a pre-trained MIR model [music2vec](https://huggingface.co/m-a-p/music2vec-v1/blob/main/README.md) before, which shares similar model structure but has weaker performance.
 
 ![Performance Comparison](mert.png)