Update README.md

README.md

@@ -1,4 +1,9 @@
 ---
+language:
+- en
+base_model:
+- google/gemma-2-9b-it
+license: gemma
 model-index:
 - name: google/Gemma-Embeddings-v1.0
   results:
@@ -352,6 +357,21 @@ model-index:
       value: 84.821
     task:
       type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB ArxivClusteringP2P (default)
+      revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
+      split: test
+      type: mteb/arxiv-clustering-p2p
+    metrics:
+    - type: v_measure
+      value: 54.8264
+    - type: v_measure_std
+      value: 14.505199999999999
+    - type: main_score
+      value: 54.8264
+    task:
+      type: Clustering
   - dataset:
       config: default
       name: MTEB ArxivClusteringS2S (default)
@@ -8627,13 +8647,9 @@ model-index:
       type: PairClassification
 tags:
 - mteb
-license: gemma
-language:
-- en
-base_model:
-- google/gemma-2-9b-it
 ---
 
+
 # Gemma Embeddings v1.0
 
 GemmaEmbed is a dense-vector embedding model, trained especially for retrieval.  As of December 12, 2024, GemmaEmbed achieves the #1 position overall on the MTEB leaderboard, with a score of 72.72.  
@@ -8665,5 +8681,4 @@ We use the [BGE-EN-ICL training data](https://huggingface.co/datasets/cfli/bge-f
 * Seungyeon Kim
 * Andrew McCallum
 * Rob Fergus
-* Manzil Zaheer
-
+* Manzil Zaheer