Update README.md

README.md

@@ -10,7 +10,8 @@ tags:
 
 # bowdpr_marco_ft
 
-This is a fine-tuned retriever on the MS-MARCO Passage Ranking Task (without distillation). We introduce a novel pre-training paradigm, Bag-of-Word Prediction, for dense retrieval. Please refer to our [paper](https://arxiv.org/abs/2401.11248) for detailed pre-training and fine-tuning settings. 
+This is a fine-tuned retriever on the MS-MARCO Passage Ranking Task (without distillation). We introduce a novel pre-training paradigm, Bag-of-Word Prediction, for dense retrieval. 
+This retriever is initialized from a base-sized pre-trained model, [bowdpr/bowdpr_marco](https://huggingface.co/bowdpr/bowdpr_marco). Please refer to our [paper](https://arxiv.org/abs/2401.11248) for detailed pre-training and fine-tuning settings. 
 
 Finetuning on MS-MARCO dataset involves a two-stage pipeline
  - s1: BM25 negs