初始化项目，由ModelHub XC社区提供模型

Model: cross-encoder/ms-marco-electra-base
Source: Original Platform

.gitattributes

@@ -0,0 +1,9 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

CEBinaryClassificationEvaluator_MS-Marco_results.csv

@@ -0,0 +1,43 @@
+epoch,steps,Accuracy,Accuracy_Threshold,F1,F1_Threshold,Precision,Recall,Average_Precision
+0,5000,0.9297070292970703,0.25256121158599854,0.8307839388145314,0.19771124422550201,0.7957875457875457,0.869,0.8904110467492587
+0,10000,0.939006099390061,0.5306986570358276,0.8460807600950118,0.28808051347732544,0.8058823529411765,0.8905,0.910544278892506
+0,15000,0.9393060693930607,0.5750397443771362,0.8566081871345029,0.48249387741088867,0.8048351648351648,0.9155,0.9132147986720082
+0,20000,0.9405059494050595,0.591253936290741,0.8546298558514537,0.570050835609436,0.8356426182513139,0.8745,0.9073685536522613
+0,25000,0.9436056394360564,0.5074090957641602,0.8603960396039605,0.5057582855224609,0.8519607843137255,0.869,0.9167379821993755
+0,30000,0.9396060393960604,0.8262588381767273,0.8542471042471043,0.7406325340270996,0.8255597014925373,0.885,0.8979176130668384
+0,35000,0.9425057494250575,0.46686679124832153,0.8596070915189268,0.28302955627441406,0.8252069917203312,0.897,0.9163289965092976
+0,40000,0.9417058294170583,0.6763133406639099,0.8575602629656682,0.6603987216949463,0.8357854769814903,0.8805,0.9173776247925393
+0,45000,0.9426057394260574,0.4643915295600891,0.8605042016806723,0.29147765040397644,0.8277136258660508,0.896,0.9120726077810245
+0,50000,0.945005499450055,0.5493776798248291,0.8624535315985131,0.4713650643825531,0.855036855036855,0.87,0.9209400105864155
+0,55000,0.9454054594540546,0.6156725287437439,0.864585893339887,0.5604670643806458,0.8501691638472693,0.8795,0.9206262233464874
+0,60000,0.9421057894210579,0.39554399251937866,0.8605827112930412,0.3811936378479004,0.8300046446818393,0.8935,0.9193948306076224
+0,65000,0.9428057194280572,0.5363738536834717,0.8629682313892841,0.32784485816955566,0.8205590622182146,0.91,0.9227492855045069
+0,70000,0.9438056194380562,0.38333064317703247,0.8628501827040195,0.3524332344532013,0.8413301662707838,0.8855,0.9236299441431376
+0,75000,0.9468053194680532,0.48936331272125244,0.8696717295443409,0.48936331272125244,0.8525456292026897,0.8875,0.9254413650794524
+0,80000,0.9454054594540546,0.3127445578575134,0.8651851851851852,0.3127445578575134,0.8546341463414634,0.876,0.9213706944185774
+0,85000,0.9443055694430557,0.31547677516937256,0.8655280250180418,0.21403872966766357,0.8340287436254057,0.8995,0.9237103419372517
+0,90000,0.9465053494650535,0.3857932686805725,0.8702401164200824,0.3761560022830963,0.8450306170513424,0.897,0.9258501989030058
+0,95000,0.9453054694530547,0.3604514002799988,0.8669713735867213,0.29048818349838257,0.8354195642095503,0.901,0.9226658871253511
+0,100000,0.9453054694530547,0.6748594045639038,0.8686288585786074,0.4552273154258728,0.8329508949059201,0.9075,0.9252677323330876
+0,105000,0.9435056494350565,0.40062007308006287,0.8639551192145862,0.1210024282336235,0.8112379280070237,0.924,0.9237990563267019
+0,110000,0.944905509449055,0.4197750985622406,0.8656429942418427,0.27975988388061523,0.8321033210332104,0.902,0.9247201058651281
+0,115000,0.9464053594640536,0.4172205924987793,0.8698167791706846,0.2961992919445038,0.839851024208566,0.902,0.927117403879296
+0,120000,0.9474052594740526,0.44686269760131836,0.8712047012732614,0.4383932948112488,0.8536468330134357,0.8895,0.9279628711835812
+0,125000,0.945005499450055,0.4358792304992676,0.8655339805825243,0.28539055585861206,0.8410377358490566,0.8915,0.9268525722856882
+0,130000,0.9462053794620537,0.21194982528686523,0.8703747911195989,0.16292141377925873,0.8328003654636821,0.9115,0.925512309638313
+0,135000,0.9454054594540546,0.2292814701795578,0.8678621991505427,0.11477036774158478,0.82171581769437,0.9195,0.9268551457216524
+0,140000,0.9482051794820517,0.31556186079978943,0.8758076094759513,0.26744428277015686,0.8398347865993575,0.915,0.9275073681003255
+0,145000,0.9478052194780522,0.3485147953033447,0.8719556305763203,0.12995882332324982,0.8421052631578947,0.904,0.9278250006342896
+0,150000,0.9483051694830517,0.32228657603263855,0.8726037369570493,0.21710461378097534,0.8477133427628477,0.899,0.9259328370035781
+0,155000,0.9474052594740526,0.1903868019580841,0.8731307284129282,0.18298938870429993,0.8434296365330848,0.905,0.9261096325445609
+0,160000,0.9473052694730527,0.5740681886672974,0.872194660996929,0.17134147882461548,0.8266905508284819,0.923,0.927973529121574
+0,165000,0.9495050494950505,0.38968273997306824,0.87591956841589,0.34622055292129517,0.8594802694898941,0.893,0.9241440163389828
+0,170000,0.9459054094590541,0.47478723526000977,0.8706669854171647,0.11328981816768646,0.8341731562070546,0.9105,0.9289979858500923
+0,175000,0.9473052694730527,0.5903739929199219,0.8703747911195989,0.15506823360919952,0.8328003654636821,0.9115,0.9305074303915251
+0,180000,0.9463053694630537,0.23235449194908142,0.8702585165498912,0.23235449194908142,0.841982234689107,0.9005,0.9291547676197442
+0,185000,0.9478052194780522,0.174373060464859,0.8734852157052836,0.171615868806839,0.8476011288805269,0.901,0.9280170204346545
+0,190000,0.949005099490051,0.5715193748474121,0.8747241971071341,0.5108739137649536,0.8581048581048581,0.892,0.9271410745170057
+0,195000,0.9461053894610539,0.5194154977798462,0.8679334916864608,0.170893132686615,0.8266968325791855,0.9135,0.9271023702066649
+0,200000,0.9468053194680532,0.3094758987426758,0.8707931277947754,0.11578939855098724,0.82258781680747,0.925,0.9290083868621436
+0,205000,0.9461053894610539,0.6028298139572144,0.8679067577113257,0.13052904605865479,0.8202047174009791,0.9215,0.9276186176796931
+0,210000,0.9459054094590541,0.49049288034439087,0.8694616484040019,0.16249723732471466,0.8303002729754322,0.9125,0.9285170114050436

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+datasets:
+- sentence-transformers/msmarco
+language:
+- en
+base_model:
+- google/electra-base-discriminator
+pipeline_tag: text-ranking
+library_name: sentence-transformers
+tags:
+- transformers
+---
+# Cross-Encoder for MS Marco
+
+This model was trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task.
+
+The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/cross_encoder/training/ms_marco)
+
+
+## Usage with SentenceTransformers
+
+The usage is easy when you have [SentenceTransformers](https://www.sbert.net/) installed. Then you can use the pre-trained models like this:
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder('cross-encoder/ms-marco-electra-base')
+scores = model.predict([
+    ("How many people live in Berlin?", "Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers."),
+    ("How many people live in Berlin?", "Berlin is well known for its museums."),
+])
+print(scores)
+# [9.9227107e-01 2.0136760e-05]
+```
+
+## Usage with Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained('model_name')
+tokenizer = AutoTokenizer.from_pretrained('model_name')
+
+features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'],  padding=True, truncation=True, return_tensors="pt")
+
+model.eval()
+with torch.no_grad():
+    scores = model(**features).logits
+    print(scores)
+```
+
+
+## Performance
+In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [TREC Deep Learning 2019](https://microsoft.github.io/TREC-2019-Deep-Learning/) and the [MS Marco Passage Reranking](https://github.com/microsoft/MSMARCO-Passage-Ranking/) dataset. 
+
+
+| Model-Name        | NDCG@10 (TREC DL 19) | MRR@10 (MS Marco Dev)  | Docs / Sec |
+| ------------- |:-------------| -----| --- | 
+| **Version 2 models** | | | 
+| cross-encoder/ms-marco-TinyBERT-L-2-v2 | 69.84 | 32.56 | 9000
+| cross-encoder/ms-marco-MiniLM-L-2-v2 | 71.01 | 34.85 | 4100
+| cross-encoder/ms-marco-MiniLM-L-4-v2 | 73.04 | 37.70 | 2500
+| cross-encoder/ms-marco-MiniLM-L-6-v2 | 74.30 | 39.01 | 1800
+| cross-encoder/ms-marco-MiniLM-L-12-v2 | 74.31 | 39.02 | 960
+| **Version 1 models** | | | 
+| cross-encoder/ms-marco-TinyBERT-L-2  | 67.43 | 30.15  | 9000
+| cross-encoder/ms-marco-TinyBERT-L-4  | 68.09 | 34.50  | 2900
+| cross-encoder/ms-marco-TinyBERT-L-6 |  69.57 | 36.13  | 680
+| cross-encoder/ms-marco-electra-base | 71.99 | 36.41 | 340
+| **Other models** | | | 
+| nboost/pt-tinybert-msmarco | 63.63 | 28.80 | 2900 
+| nboost/pt-bert-base-uncased-msmarco | 70.94 | 34.75 | 340 
+| nboost/pt-bert-large-msmarco | 73.36 | 36.48 | 100 
+| Capreolus/electra-base-msmarco | 71.23 | 36.89 | 340 
+| amberoad/bert-multilingual-passage-reranking-msmarco | 68.40 | 35.54 | 330 
+| sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco | 72.82 | 37.88 | 720
+ 
+ Note: Runtime was computed on a V100 GPU.

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13cb549da5498feba1295402742e50f7e4452f043dffdc38066fdb8fb499a6b
+size 437960356

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3e674221713a05fe4d651d5258edf8911a99f34821e243146bc0d21e970d68
+size 438212375

onnx/model_O1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759510ff60613f174e7d819be3287174ec87a8bf36f00959b89183089a359ec6
+size 438103492

onnx/model_O2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219c2086a10d570fc1fffeca352e1521b6551eb7dcac99150f157a0f69062334
+size 437971485

onnx/model_O3.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a17242a7a5ea6b3afed1c7ddefaf2f272fac890cfc9facb38a3a87882f6b116
+size 437971327

onnx/model_O4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077075bbf7f6a188d8627b5ed4dab90ea3894e24760b1fe4bd5126006fe29f27
+size 219012097

onnx/model_qint8_arm64.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e4292facfac9eacaed6f16b15b775009f1d4ae1475766d4e5ed6b1ca8aca24
+size 110780504

onnx/model_qint8_avx512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e4292facfac9eacaed6f16b15b775009f1d4ae1475766d4e5ed6b1ca8aca24
+size 110780504

onnx/model_qint8_avx512_vnni.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e4292facfac9eacaed6f16b15b775009f1d4ae1475766d4e5ed6b1ca8aca24
+size 110780504

onnx/model_quint8_avx2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6abd7acd1ae45a4f0b0400e7d9ffc1796e637179383e889077a565b374f01a
+size 110780501

openvino/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed47c86dd5e29b2f1818339860fe29270b909bb542568f2ec4e47dcd93c93e88
+size 437936264

openvino/openvino_model_qint8_quantized.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ac4a491328885b80bac33c95940c8cdde98c240d18ba9301d90adc747aadd6
+size 110577356

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c554473d61458bf2969566b1bb464eb280ef7de9cacb6ec787b4fe7f0a9a80d9
+size 438022601

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}