Update README.md

README.md

@@ -10,11 +10,11 @@ tags:
 
 This model is trained through the approach described in [DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management](https://www.arxiv.org/abs/2510.15087). 
 The associated GitHub repository is available [here](https://github.com/KaiYin97/DMRETRIEVER).
-This model has 596 parameters and it is the pre-trained version (trained using only unlabeled dataset containing in-batch negative).
+This model has 596M parameters and it is the pre-trained version (trained using only unlabeled dataset containing in-batch negative).
 
 ## 🧠 Model Overview
 
-**DMRetriever-596M** has the following features:
+**DMRetriever-596M-PT** has the following features:
 
 - Model Type: Text Embedding
 - Supported Languages: English
@@ -52,7 +52,7 @@ import torch.nn.functional as F
 from transformers import AutoTokenizer
 from bidirectional_qwen3 import Qwen3BiModel  # custom bidirectional backbone
 
-MODEL_ID = "DMIR01/DMRetriever-4B"
+MODEL_ID = "DMIR01/DMRetriever-596M-PT"
 
 # Device & dtype
 device = "cuda" if torch.cuda.is_available() else "cpu"