Upload README.md

README.md

@@ -0,0 +1,669 @@
+---
+model-index:
+- name: XYZ-embedding-zh-v2
+  results:
+  - dataset:
+      config: default
+      name: MTEB CMedQAv1
+      revision: None
+      split: test
+      type: C-MTEB/CMedQAv1
+    metrics:
+    - type: map
+      value: 89.9766367822762
+    - type: mrr
+      value: 91.88896825396824
+    - type: main_score
+      value: 89.9766367822762
+    task:
+      type: Reranking
+  - dataset:
+      config: default
+      name: MTEB CMedQAv2
+      revision: None
+      split: test
+      type: C-MTEB/CMedQAv2
+    metrics:
+    - type: map
+      value: 89.04628340075982
+    - type: mrr
+      value: 91.21702380952381
+    - type: main_score
+      value: 89.04628340075982
+    task:
+      type: Reranking
+  - dataset:
+      config: default
+      name: MTEB CmedqaRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/CmedqaRetrieval
+    metrics:
+    - type: map_at_1
+      value: 27.796
+    - type: map_at_10
+      value: 41.498000000000005
+    - type: map_at_100
+      value: 43.332
+    - type: map_at_1000
+      value: 43.429
+    - type: map_at_3
+      value: 37.172
+    - type: map_at_5
+      value: 39.617000000000004
+    - type: mrr_at_1
+      value: 42.111
+    - type: mrr_at_10
+      value: 50.726000000000006
+    - type: mrr_at_100
+      value: 51.632
+    - type: mrr_at_1000
+      value: 51.67
+    - type: mrr_at_3
+      value: 48.429
+    - type: mrr_at_5
+      value: 49.662
+    - type: ndcg_at_1
+      value: 42.111
+    - type: ndcg_at_10
+      value: 48.294
+    - type: ndcg_at_100
+      value: 55.135999999999996
+    - type: ndcg_at_1000
+      value: 56.818000000000005
+    - type: ndcg_at_3
+      value: 43.185
+    - type: ndcg_at_5
+      value: 45.266
+    - type: precision_at_1
+      value: 42.111
+    - type: precision_at_10
+      value: 10.635
+    - type: precision_at_100
+      value: 1.619
+    - type: precision_at_1000
+      value: 0.183
+    - type: precision_at_3
+      value: 24.539
+    - type: precision_at_5
+      value: 17.644000000000002
+    - type: recall_at_1
+      value: 27.796
+    - type: recall_at_10
+      value: 59.034
+    - type: recall_at_100
+      value: 86.991
+    - type: recall_at_1000
+      value: 98.304
+    - type: recall_at_3
+      value: 43.356
+    - type: recall_at_5
+      value: 49.998
+    - type: main_score
+      value: 48.294
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB CovidRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/CovidRetrieval
+    metrics:
+    - type: map_at_1
+      value: 80.479
+    - type: map_at_10
+      value: 87.984
+    - type: map_at_100
+      value: 88.036
+    - type: map_at_1000
+      value: 88.03699999999999
+    - type: map_at_3
+      value: 87.083
+    - type: map_at_5
+      value: 87.694
+    - type: mrr_at_1
+      value: 80.927
+    - type: mrr_at_10
+      value: 88.046
+    - type: mrr_at_100
+      value: 88.099
+    - type: mrr_at_1000
+      value: 88.1
+    - type: mrr_at_3
+      value: 87.215
+    - type: mrr_at_5
+      value: 87.768
+    - type: ndcg_at_1
+      value: 80.927
+    - type: ndcg_at_10
+      value: 90.756
+    - type: ndcg_at_100
+      value: 90.96
+    - type: ndcg_at_1000
+      value: 90.975
+    - type: ndcg_at_3
+      value: 89.032
+    - type: ndcg_at_5
+      value: 90.106
+    - type: precision_at_1
+      value: 80.927
+    - type: precision_at_10
+      value: 10.011000000000001
+    - type: precision_at_100
+      value: 1.009
+    - type: precision_at_1000
+      value: 0.101
+    - type: precision_at_3
+      value: 31.752999999999997
+    - type: precision_at_5
+      value: 19.6
+    - type: recall_at_1
+      value: 80.479
+    - type: recall_at_10
+      value: 99.05199999999999
+    - type: recall_at_100
+      value: 99.895
+    - type: recall_at_1000
+      value: 100.0
+    - type: recall_at_3
+      value: 94.494
+    - type: recall_at_5
+      value: 97.102
+    - type: main_score
+      value: 90.756
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB DuRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/DuRetrieval
+    metrics:
+    - type: map_at_1
+      value: 27.853
+    - type: map_at_10
+      value: 85.13199999999999
+    - type: map_at_100
+      value: 87.688
+    - type: map_at_1000
+      value: 87.712
+    - type: map_at_3
+      value: 59.705
+    - type: map_at_5
+      value: 75.139
+    - type: mrr_at_1
+      value: 93.65
+    - type: mrr_at_10
+      value: 95.682
+    - type: mrr_at_100
+      value: 95.722
+    - type: mrr_at_1000
+      value: 95.724
+    - type: mrr_at_3
+      value: 95.467
+    - type: mrr_at_5
+      value: 95.612
+    - type: ndcg_at_1
+      value: 93.65
+    - type: ndcg_at_10
+      value: 91.155
+    - type: ndcg_at_100
+      value: 93.183
+    - type: ndcg_at_1000
+      value: 93.38499999999999
+    - type: ndcg_at_3
+      value: 90.648
+    - type: ndcg_at_5
+      value: 89.47699999999999
+    - type: precision_at_1
+      value: 93.65
+    - type: precision_at_10
+      value: 43.11
+    - type: precision_at_100
+      value: 4.854
+    - type: precision_at_1000
+      value: 0.49100000000000005
+    - type: precision_at_3
+      value: 81.11699999999999
+    - type: precision_at_5
+      value: 68.28999999999999
+    - type: recall_at_1
+      value: 27.853
+    - type: recall_at_10
+      value: 91.678
+    - type: recall_at_100
+      value: 98.553
+    - type: recall_at_1000
+      value: 99.553
+    - type: recall_at_3
+      value: 61.381
+    - type: recall_at_5
+      value: 78.605
+    - type: main_score
+      value: 91.155
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB EcomRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/EcomRetrieval
+    metrics:
+    - type: map_at_1
+      value: 54.50000000000001
+    - type: map_at_10
+      value: 65.167
+    - type: map_at_100
+      value: 65.664
+    - type: map_at_1000
+      value: 65.67399999999999
+    - type: map_at_3
+      value: 62.633
+    - type: map_at_5
+      value: 64.208
+    - type: mrr_at_1
+      value: 54.50000000000001
+    - type: mrr_at_10
+      value: 65.167
+    - type: mrr_at_100
+      value: 65.664
+    - type: mrr_at_1000
+      value: 65.67399999999999
+    - type: mrr_at_3
+      value: 62.633
+    - type: mrr_at_5
+      value: 64.208
+    - type: ndcg_at_1
+      value: 54.50000000000001
+    - type: ndcg_at_10
+      value: 70.294
+    - type: ndcg_at_100
+      value: 72.564
+    - type: ndcg_at_1000
+      value: 72.841
+    - type: ndcg_at_3
+      value: 65.128
+    - type: ndcg_at_5
+      value: 67.96799999999999
+    - type: precision_at_1
+      value: 54.50000000000001
+    - type: precision_at_10
+      value: 8.64
+    - type: precision_at_100
+      value: 0.967
+    - type: precision_at_1000
+      value: 0.099
+    - type: precision_at_3
+      value: 24.099999999999998
+    - type: precision_at_5
+      value: 15.840000000000002
+    - type: recall_at_1
+      value: 54.50000000000001
+    - type: recall_at_10
+      value: 86.4
+    - type: recall_at_100
+      value: 96.7
+    - type: recall_at_1000
+      value: 98.9
+    - type: recall_at_3
+      value: 72.3
+    - type: recall_at_5
+      value: 79.2
+    - type: main_score
+      value: 70.294
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB MMarcoReranking
+      revision: None
+      split: dev
+      type: C-MTEB/Mmarco-reranking
+    metrics:
+    - type: map
+      value: 37.68251937316638
+    - type: mrr
+      value: 36.61746031746032
+    - type: main_score
+      value: 37.68251937316638
+    task:
+      type: Reranking
+  - dataset:
+      config: default
+      name: MTEB MMarcoRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/MMarcoRetrieval
+    metrics:
+    - type: map_at_1
+      value: 69.401
+    - type: map_at_10
+      value: 78.8
+    - type: map_at_100
+      value: 79.077
+    - type: map_at_1000
+      value: 79.081
+    - type: map_at_3
+      value: 76.97
+    - type: map_at_5
+      value: 78.185
+    - type: mrr_at_1
+      value: 71.719
+    - type: mrr_at_10
+      value: 79.327
+    - type: mrr_at_100
+      value: 79.56400000000001
+    - type: mrr_at_1000
+      value: 79.56800000000001
+    - type: mrr_at_3
+      value: 77.736
+    - type: mrr_at_5
+      value: 78.782
+    - type: ndcg_at_1
+      value: 71.719
+    - type: ndcg_at_10
+      value: 82.505
+    - type: ndcg_at_100
+      value: 83.673
+    - type: ndcg_at_1000
+      value: 83.786
+    - type: ndcg_at_3
+      value: 79.07600000000001
+    - type: ndcg_at_5
+      value: 81.122
+    - type: precision_at_1
+      value: 71.719
+    - type: precision_at_10
+      value: 9.924
+    - type: precision_at_100
+      value: 1.049
+    - type: precision_at_1000
+      value: 0.106
+    - type: precision_at_3
+      value: 29.742
+    - type: precision_at_5
+      value: 18.937
+    - type: recall_at_1
+      value: 69.401
+    - type: recall_at_10
+      value: 93.349
+    - type: recall_at_100
+      value: 98.492
+    - type: recall_at_1000
+      value: 99.384
+    - type: recall_at_3
+      value: 84.385
+    - type: recall_at_5
+      value: 89.237
+    - type: main_score
+      value: 82.505
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB MedicalRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/MedicalRetrieval
+    metrics:
+    - type: map_at_1
+      value: 57.8
+    - type: map_at_10
+      value: 64.696
+    - type: map_at_100
+      value: 65.294
+    - type: map_at_1000
+      value: 65.328
+    - type: map_at_3
+      value: 62.949999999999996
+    - type: map_at_5
+      value: 64.095
+    - type: mrr_at_1
+      value: 58.099999999999994
+    - type: mrr_at_10
+      value: 64.85
+    - type: mrr_at_100
+      value: 65.448
+    - type: mrr_at_1000
+      value: 65.482
+    - type: mrr_at_3
+      value: 63.1
+    - type: mrr_at_5
+      value: 64.23
+    - type: ndcg_at_1
+      value: 57.8
+    - type: ndcg_at_10
+      value: 68.041
+    - type: ndcg_at_100
+      value: 71.074
+    - type: ndcg_at_1000
+      value: 71.919
+    - type: ndcg_at_3
+      value: 64.584
+    - type: ndcg_at_5
+      value: 66.625
+    - type: precision_at_1
+      value: 57.8
+    - type: precision_at_10
+      value: 7.85
+    - type: precision_at_100
+      value: 0.9289999999999999
+    - type: precision_at_1000
+      value: 0.099
+    - type: precision_at_3
+      value: 23.1
+    - type: precision_at_5
+      value: 14.84
+    - type: recall_at_1
+      value: 57.8
+    - type: recall_at_10
+      value: 78.5
+    - type: recall_at_100
+      value: 92.9
+    - type: recall_at_1000
+      value: 99.4
+    - type: recall_at_3
+      value: 69.3
+    - type: recall_at_5
+      value: 74.2
+    - type: main_score
+      value: 68.041
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB T2Reranking
+      revision: None
+      split: dev
+      type: C-MTEB/T2Reranking
+    metrics:
+    - type: map
+      value: 69.13287570713865
+    - type: mrr
+      value: 79.95326487625066
+    - type: main_score
+      value: 69.13287570713865
+    task:
+      type: Reranking
+  - dataset:
+      config: default
+      name: MTEB T2Retrieval
+      revision: None
+      split: dev
+      type: C-MTEB/T2Retrieval
+    metrics:
+    - type: map_at_1
+      value: 28.041
+    - type: map_at_10
+      value: 78.509
+    - type: map_at_100
+      value: 82.083
+    - type: map_at_1000
+      value: 82.143
+    - type: map_at_3
+      value: 55.345
+    - type: map_at_5
+      value: 67.899
+    - type: mrr_at_1
+      value: 90.86
+    - type: mrr_at_10
+      value: 93.31
+    - type: mrr_at_100
+      value: 93.388
+    - type: mrr_at_1000
+      value: 93.391
+    - type: mrr_at_3
+      value: 92.92200000000001
+    - type: mrr_at_5
+      value: 93.167
+    - type: ndcg_at_1
+      value: 90.86
+    - type: ndcg_at_10
+      value: 85.875
+    - type: ndcg_at_100
+      value: 89.269
+    - type: ndcg_at_1000
+      value: 89.827
+    - type: ndcg_at_3
+      value: 87.254
+    - type: ndcg_at_5
+      value: 85.855
+    - type: precision_at_1
+      value: 90.86
+    - type: precision_at_10
+      value: 42.488
+    - type: precision_at_100
+      value: 5.029
+    - type: precision_at_1000
+      value: 0.516
+    - type: precision_at_3
+      value: 76.172
+    - type: precision_at_5
+      value: 63.759
+    - type: recall_at_1
+      value: 28.041
+    - type: recall_at_10
+      value: 84.829
+    - type: recall_at_100
+      value: 95.89999999999999
+    - type: recall_at_1000
+      value: 98.665
+    - type: recall_at_3
+      value: 57.009
+    - type: recall_at_5
+      value: 71.188
+    - type: main_score
+      value: 85.875
+    task:
+      type: Retrieval
+  - dataset:
+      config: default
+      name: MTEB VideoRetrieval
+      revision: None
+      split: dev
+      type: C-MTEB/VideoRetrieval
+    metrics:
+    - type: map_at_1
+      value: 67.30000000000001
+    - type: map_at_10
+      value: 76.819
+    - type: map_at_100
+      value: 77.141
+    - type: map_at_1000
+      value: 77.142
+    - type: map_at_3
+      value: 75.233
+    - type: map_at_5
+      value: 76.163
+    - type: mrr_at_1
+      value: 67.30000000000001
+    - type: mrr_at_10
+      value: 76.819
+    - type: mrr_at_100
+      value: 77.141
+    - type: mrr_at_1000
+      value: 77.142
+    - type: mrr_at_3
+      value: 75.233
+    - type: mrr_at_5
+      value: 76.163
+    - type: ndcg_at_1
+      value: 67.30000000000001
+    - type: ndcg_at_10
+      value: 80.93599999999999
+    - type: ndcg_at_100
+      value: 82.311
+    - type: ndcg_at_1000
+      value: 82.349
+    - type: ndcg_at_3
+      value: 77.724
+    - type: ndcg_at_5
+      value: 79.406
+    - type: precision_at_1
+      value: 67.30000000000001
+    - type: precision_at_10
+      value: 9.36
+    - type: precision_at_100
+      value: 0.996
+    - type: precision_at_1000
+      value: 0.1
+    - type: precision_at_3
+      value: 28.299999999999997
+    - type: precision_at_5
+      value: 17.8
+    - type: recall_at_1
+      value: 67.30000000000001
+    - type: recall_at_10
+      value: 93.60000000000001
+    - type: recall_at_100
+      value: 99.6
+    - type: recall_at_1000
+      value: 99.9
+    - type: recall_at_3
+      value: 84.89999999999999
+    - type: recall_at_5
+      value: 89.0
+    - type: main_score
+      value: 80.93599999999999
+    task:
+      type: Retrieval
+tags:
+- mteb
+language:
+- zh
+
+---
+
+<h2 align="left">XYZ-embedding-zh-v2</h2>
+
+## Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("fangxq/XYZ-embedding-zh-v2")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1792]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```