Upload folder using huggingface_hub

README.md

@@ -31,6 +31,15 @@ Our model primarily demonstrates the following capabilities:
 
 We will release a technical report about lightweight reranker soon with more details.
 
+------
+
+You can use **bge-reranker-v2.5-gemma2-lightweight** with the following different prompts:
+
+- Predict whether passage B contains an answer to query A.
+- Predict whether passages A and B have the same meaning.
+- Predict whether queries A and B are asking the same thing.
+- Predict whether argument A and counterargument B express contradictory opinions.
+
 
 ## Model List
 
@@ -360,6 +369,8 @@ with torch.no_grad():
 
 ## Evaluation
 
+Where the configuration of saving 60% Flops is: `compress_ratios=2`, `compress_layer=[8]`, `cutoff_layers=[25]`.
+
 - **BEIR:**
 
 |        BEIR        | bge-large-en-v1.5 | Bge-rearanker v2 m3 | jina-reranker-v2-base-multilingual | bge-reranker-v2-gemma | bge-reranker-v2.5-gemma2-lightweight | bge-reranker-v2.5-gemma2-lightweight |