Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,619 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- mteb
+model-index:
+- name: cloudy-large-zh
+  results:
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/CMedQAv1-reranking
+      name: MTEB CMedQAv1
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map
+      value: 86.10362876754219
+    - type: mrr
+      value: 88.77880952380951
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/CMedQAv2-reranking
+      name: MTEB CMedQAv2
+      config: default
+      split: test
+      revision: None
+    metrics:
+    - type: map
+      value: 86.94664825874587
+    - type: mrr
+      value: 89.47257936507937
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/CmedqaRetrieval
+      name: MTEB CmedqaRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 25.296999999999997
+    - type: map_at_10
+      value: 37.159
+    - type: map_at_100
+      value: 39.016
+    - type: map_at_1000
+      value: 39.134
+    - type: map_at_3
+      value: 33.248
+    - type: map_at_5
+      value: 35.371
+    - type: mrr_at_1
+      value: 38.435
+    - type: mrr_at_10
+      value: 46.235
+    - type: mrr_at_100
+      value: 47.265
+    - type: mrr_at_1000
+      value: 47.308
+    - type: mrr_at_3
+      value: 43.828
+    - type: mrr_at_5
+      value: 45.21
+    - type: ndcg_at_1
+      value: 38.435
+    - type: ndcg_at_10
+      value: 43.578
+    - type: ndcg_at_100
+      value: 50.995000000000005
+    - type: ndcg_at_1000
+      value: 53.012
+    - type: ndcg_at_3
+      value: 38.667
+    - type: ndcg_at_5
+      value: 40.657
+    - type: precision_at_1
+      value: 38.435
+    - type: precision_at_10
+      value: 9.607000000000001
+    - type: precision_at_100
+      value: 1.557
+    - type: precision_at_1000
+      value: 0.182
+    - type: precision_at_3
+      value: 21.714
+    - type: precision_at_5
+      value: 15.634
+    - type: recall_at_1
+      value: 25.296999999999997
+    - type: recall_at_10
+      value: 53.408
+    - type: recall_at_100
+      value: 84.202
+    - type: recall_at_1000
+      value: 97.61
+    - type: recall_at_3
+      value: 38.533
+    - type: recall_at_5
+      value: 44.927
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/CovidRetrieval
+      name: MTEB CovidRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 74.763
+    - type: map_at_10
+      value: 82.604
+    - type: map_at_100
+      value: 82.795
+    - type: map_at_1000
+      value: 82.798
+    - type: map_at_3
+      value: 81.437
+    - type: map_at_5
+      value: 82.097
+    - type: mrr_at_1
+      value: 74.816
+    - type: mrr_at_10
+      value: 82.601
+    - type: mrr_at_100
+      value: 82.787
+    - type: mrr_at_1000
+      value: 82.78999999999999
+    - type: mrr_at_3
+      value: 81.472
+    - type: mrr_at_5
+      value: 82.146
+    - type: ndcg_at_1
+      value: 74.921
+    - type: ndcg_at_10
+      value: 85.83
+    - type: ndcg_at_100
+      value: 86.655
+    - type: ndcg_at_1000
+      value: 86.748
+    - type: ndcg_at_3
+      value: 83.497
+    - type: ndcg_at_5
+      value: 84.696
+    - type: precision_at_1
+      value: 74.921
+    - type: precision_at_10
+      value: 9.663
+    - type: precision_at_100
+      value: 1.0030000000000001
+    - type: precision_at_1000
+      value: 0.101
+    - type: precision_at_3
+      value: 29.996000000000002
+    - type: precision_at_5
+      value: 18.609
+    - type: recall_at_1
+      value: 74.763
+    - type: recall_at_10
+      value: 95.627
+    - type: recall_at_100
+      value: 99.262
+    - type: recall_at_1000
+      value: 100.0
+    - type: recall_at_3
+      value: 89.357
+    - type: recall_at_5
+      value: 92.255
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/DuRetrieval
+      name: MTEB DuRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 26.021
+    - type: map_at_10
+      value: 78.561
+    - type: map_at_100
+      value: 81.291
+    - type: map_at_1000
+      value: 81.34400000000001
+    - type: map_at_3
+      value: 54.55799999999999
+    - type: map_at_5
+      value: 68.804
+    - type: mrr_at_1
+      value: 89.8
+    - type: mrr_at_10
+      value: 92.905
+    - type: mrr_at_100
+      value: 92.976
+    - type: mrr_at_1000
+      value: 92.979
+    - type: mrr_at_3
+      value: 92.608
+    - type: mrr_at_5
+      value: 92.783
+    - type: ndcg_at_1
+      value: 89.8
+    - type: ndcg_at_10
+      value: 86.203
+    - type: ndcg_at_100
+      value: 88.955
+    - type: ndcg_at_1000
+      value: 89.442
+    - type: ndcg_at_3
+      value: 85.163
+    - type: ndcg_at_5
+      value: 84.057
+    - type: precision_at_1
+      value: 89.8
+    - type: precision_at_10
+      value: 41.175
+    - type: precision_at_100
+      value: 4.744000000000001
+    - type: precision_at_1000
+      value: 0.486
+    - type: precision_at_3
+      value: 76.283
+    - type: precision_at_5
+      value: 64.41
+    - type: recall_at_1
+      value: 26.021
+    - type: recall_at_10
+      value: 87.25
+    - type: recall_at_100
+      value: 96.154
+    - type: recall_at_1000
+      value: 98.615
+    - type: recall_at_3
+      value: 56.830999999999996
+    - type: recall_at_5
+      value: 73.518
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/EcomRetrieval
+      name: MTEB EcomRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 52.300000000000004
+    - type: map_at_10
+      value: 62.149
+    - type: map_at_100
+      value: 62.719
+    - type: map_at_1000
+      value: 62.73
+    - type: map_at_3
+      value: 59.767
+    - type: map_at_5
+      value: 61.232
+    - type: mrr_at_1
+      value: 52.300000000000004
+    - type: mrr_at_10
+      value: 62.149
+    - type: mrr_at_100
+      value: 62.719
+    - type: mrr_at_1000
+      value: 62.73
+    - type: mrr_at_3
+      value: 59.767
+    - type: mrr_at_5
+      value: 61.232
+    - type: ndcg_at_1
+      value: 52.300000000000004
+    - type: ndcg_at_10
+      value: 66.99300000000001
+    - type: ndcg_at_100
+      value: 69.672
+    - type: ndcg_at_1000
+      value: 69.95400000000001
+    - type: ndcg_at_3
+      value: 62.166
+    - type: ndcg_at_5
+      value: 64.804
+    - type: precision_at_1
+      value: 52.300000000000004
+    - type: precision_at_10
+      value: 8.219999999999999
+    - type: precision_at_100
+      value: 0.9450000000000001
+    - type: precision_at_1000
+      value: 0.097
+    - type: precision_at_3
+      value: 23.033
+    - type: precision_at_5
+      value: 15.1
+    - type: recall_at_1
+      value: 52.300000000000004
+    - type: recall_at_10
+      value: 82.19999999999999
+    - type: recall_at_100
+      value: 94.5
+    - type: recall_at_1000
+      value: 96.7
+    - type: recall_at_3
+      value: 69.1
+    - type: recall_at_5
+      value: 75.5
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/Mmarco-reranking
+      name: MTEB MMarcoReranking
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map
+      value: 24.260352944026806
+    - type: mrr
+      value: 22.69484126984127
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/MMarcoRetrieval
+      name: MTEB MMarcoRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 64.888
+    - type: map_at_10
+      value: 73.921
+    - type: map_at_100
+      value: 74.28099999999999
+    - type: map_at_1000
+      value: 74.295
+    - type: map_at_3
+      value: 72.04
+    - type: map_at_5
+      value: 73.207
+    - type: mrr_at_1
+      value: 67.092
+    - type: mrr_at_10
+      value: 74.547
+    - type: mrr_at_100
+      value: 74.862
+    - type: mrr_at_1000
+      value: 74.875
+    - type: mrr_at_3
+      value: 72.908
+    - type: mrr_at_5
+      value: 73.936
+    - type: ndcg_at_1
+      value: 67.092
+    - type: ndcg_at_10
+      value: 77.687
+    - type: ndcg_at_100
+      value: 79.24600000000001
+    - type: ndcg_at_1000
+      value: 79.60000000000001
+    - type: ndcg_at_3
+      value: 74.124
+    - type: ndcg_at_5
+      value: 76.098
+    - type: precision_at_1
+      value: 67.092
+    - type: precision_at_10
+      value: 9.424000000000001
+    - type: precision_at_100
+      value: 1.019
+    - type: precision_at_1000
+      value: 0.105
+    - type: precision_at_3
+      value: 27.927000000000003
+    - type: precision_at_5
+      value: 17.797
+    - type: recall_at_1
+      value: 64.888
+    - type: recall_at_10
+      value: 88.672
+    - type: recall_at_100
+      value: 95.599
+    - type: recall_at_1000
+      value: 98.337
+    - type: recall_at_3
+      value: 79.27499999999999
+    - type: recall_at_5
+      value: 83.96000000000001
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/MedicalRetrieval
+      name: MTEB MedicalRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 55.50000000000001
+    - type: map_at_10
+      value: 61.316
+    - type: map_at_100
+      value: 61.832
+    - type: map_at_1000
+      value: 61.867000000000004
+    - type: map_at_3
+      value: 59.9
+    - type: map_at_5
+      value: 60.685
+    - type: mrr_at_1
+      value: 55.7
+    - type: mrr_at_10
+      value: 61.416000000000004
+    - type: mrr_at_100
+      value: 61.931999999999995
+    - type: mrr_at_1000
+      value: 61.967000000000006
+    - type: mrr_at_3
+      value: 60.0
+    - type: mrr_at_5
+      value: 60.785
+    - type: ndcg_at_1
+      value: 55.50000000000001
+    - type: ndcg_at_10
+      value: 64.228
+    - type: ndcg_at_100
+      value: 67.04599999999999
+    - type: ndcg_at_1000
+      value: 68.176
+    - type: ndcg_at_3
+      value: 61.314
+    - type: ndcg_at_5
+      value: 62.743
+    - type: precision_at_1
+      value: 55.50000000000001
+    - type: precision_at_10
+      value: 7.340000000000001
+    - type: precision_at_100
+      value: 0.873
+    - type: precision_at_1000
+      value: 0.097
+    - type: precision_at_3
+      value: 21.8
+    - type: precision_at_5
+      value: 13.780000000000001
+    - type: recall_at_1
+      value: 55.50000000000001
+    - type: recall_at_10
+      value: 73.4
+    - type: recall_at_100
+      value: 87.3
+    - type: recall_at_1000
+      value: 96.6
+    - type: recall_at_3
+      value: 65.4
+    - type: recall_at_5
+      value: 68.89999999999999
+  - task:
+      type: Reranking
+    dataset:
+      type: C-MTEB/T2Reranking
+      name: MTEB T2Reranking
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map
+      value: 66.83154421352779
+    - type: mrr
+      value: 76.27995669041708
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/T2Retrieval
+      name: MTEB T2Retrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 28.303
+    - type: map_at_10
+      value: 76.943
+    - type: map_at_100
+      value: 80.585
+    - type: map_at_1000
+      value: 80.657
+    - type: map_at_3
+      value: 54.818999999999996
+    - type: map_at_5
+      value: 66.854
+    - type: mrr_at_1
+      value: 90.742
+    - type: mrr_at_10
+      value: 93.496
+    - type: mrr_at_100
+      value: 93.55799999999999
+    - type: mrr_at_1000
+      value: 93.56
+    - type: mrr_at_3
+      value: 93.083
+    - type: mrr_at_5
+      value: 93.349
+    - type: ndcg_at_1
+      value: 90.742
+    - type: ndcg_at_10
+      value: 84.94
+    - type: ndcg_at_100
+      value: 88.616
+    - type: ndcg_at_1000
+      value: 89.25
+    - type: ndcg_at_3
+      value: 86.58200000000001
+    - type: ndcg_at_5
+      value: 85.018
+    - type: precision_at_1
+      value: 90.742
+    - type: precision_at_10
+      value: 41.507
+    - type: precision_at_100
+      value: 4.984999999999999
+    - type: precision_at_1000
+      value: 0.515
+    - type: precision_at_3
+      value: 75.101
+    - type: precision_at_5
+      value: 62.543000000000006
+    - type: recall_at_1
+      value: 28.303
+    - type: recall_at_10
+      value: 83.895
+    - type: recall_at_100
+      value: 95.537
+    - type: recall_at_1000
+      value: 98.558
+    - type: recall_at_3
+      value: 56.679
+    - type: recall_at_5
+      value: 70.535
+  - task:
+      type: Retrieval
+    dataset:
+      type: C-MTEB/VideoRetrieval
+      name: MTEB VideoRetrieval
+      config: default
+      split: dev
+      revision: None
+    metrics:
+    - type: map_at_1
+      value: 59.5
+    - type: map_at_10
+      value: 69.53
+    - type: map_at_100
+      value: 69.976
+    - type: map_at_1000
+      value: 69.99300000000001
+    - type: map_at_3
+      value: 67.85
+    - type: map_at_5
+      value: 68.83
+    - type: mrr_at_1
+      value: 59.5
+    - type: mrr_at_10
+      value: 69.53
+    - type: mrr_at_100
+      value: 69.976
+    - type: mrr_at_1000
+      value: 69.99300000000001
+    - type: mrr_at_3
+      value: 67.85
+    - type: mrr_at_5
+      value: 68.83
+    - type: ndcg_at_1
+      value: 59.5
+    - type: ndcg_at_10
+      value: 73.855
+    - type: ndcg_at_100
+      value: 75.831
+    - type: ndcg_at_1000
+      value: 76.227
+    - type: ndcg_at_3
+      value: 70.418
+    - type: ndcg_at_5
+      value: 72.18599999999999
+    - type: precision_at_1
+      value: 59.5
+    - type: precision_at_10
+      value: 8.72
+    - type: precision_at_100
+      value: 0.96
+    - type: precision_at_1000
+      value: 0.099
+    - type: precision_at_3
+      value: 25.933
+    - type: precision_at_5
+      value: 16.42
+    - type: recall_at_1
+      value: 59.5
+    - type: recall_at_10
+      value: 87.2
+    - type: recall_at_100
+      value: 96.0
+    - type: recall_at_1000
+      value: 99.0
+    - type: recall_at_3
+      value: 77.8
+    - type: recall_at_5
+      value: 82.1
+---
+
+| Model Name      | Dimension | Sequence Length | Language | Need instruction for retrieval? |
+| --------------- | --------- | --------------- | -------- | ------------------------------- |
+| cloudy-largh-zh | 1024      | 1024            | Chinese  | NO                              |

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "akarum/cloudy-large-zh",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.35.2",
+    "pytorch": "2.0.1+cu117"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a40e27c61ee1e815e415c72cd2e046cfebb929bee2910848ed3a8f47849b3e
+size 1304231728

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 1024,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1024,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}