Update README.md

README.md

@@ -35,15 +35,15 @@ Training objective:
 
 ---
 
-## 🚀 Usage
+## 🚀 Usage - Text Similarity
 
 ```python
 from transformers import AutoTokenizer, AutoModel
 import torch
 import torch.nn.functional as F
 
-tokenizer = AutoTokenizer.from_pretrained("your-username/biohicl-base")
-model = AutoModel.from_pretrained("your-username/biohicl-base")
+tokenizer = AutoTokenizer.from_pretrained("LunaLan07/BioHiCL-Large")
+model = AutoModel.from_pretrained("LunaLan07/BioHiCL-Large")
 
 def encode(texts):
     inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")
@@ -58,8 +58,36 @@ doc = encode(["Chronic obstructive pulmonary disease is treated with bronchodila
 similarity = (query @ doc.T).item()
 print(similarity)
 
-## 📖 Citation
 
+
+---
+
+## 🚀 Usage - Evaluation on BEIR Benchmark
+
+```python
+from beir import util
+from beir.datasets.data_loader import GenericDataLoader
+from beir.retrieval.models import SentenceBERT
+from beir.retrieval.search.dense import DenseRetrievalExactSearch
+from beir.retrieval.evaluation import EvaluateRetrieval
+
+dataset = "scifact"
+url = ...
+data_path = util.download_and_unzip(url, "datasets")
+corpus, queries, qrels = GenericDataLoader(data_path).load(split="test")
+
+model_name = "LunaLan07/BioHiCL-Large"
+model = SentenceBERT(model_name)
+retriever = DenseRetrievalExactSearch(model, batch_size=16)
+top_k = 10  # top 10 documents per query
+results = retriever.search(corpus, queries, top_k=top_k, score_function="cos_sim")
+
+k_values = [1, 3, 5, 10]
+ndcg, _map, recall, precision = EvaluateRetrieval.evaluate(qrels, results, k_values=k_values)
+
+---
+
+## 📖 Citation
 If you use this model, please cite:
 
 ```bibtex