Add new SentenceTransformer model.

.gitattributes

@@ -30,3 +30,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,129 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 11781 with parameters:
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 5,
+    "evaluation_steps": 1178,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 1e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 5891,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "models/multi-qa-mpnet-zh/",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.21.1",
+    "pytorch": "1.12.1+cu102"
+  }
+}

eval/binary_classification_evaluation_dev_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
+0,1178,0.9859318698410396,0.766584038734436,0.5917520425366359,0.5779607346421786,0.6062176165803109,0.7114009857177734,0.6106917399103134,0.9850966840121927,14.191865921020508,0.5428318704497517,0.5563458856345885,0.5299588149329082,15.487773895263672,0.552094194228552,0.9850766795612024,0.6668289303779602,0.5418947639595544,0.525875,0.558921216952305,0.7475653886795044,0.5508813800697162,0.9835613423986838,0.8766357898712158,0.47722628699492453,0.4735740450026164,0.48093529958814935,0.7481151819229126,0.46071058903669637
+0,2356,0.9870921279984797,0.7470366954803467,0.6312380952380952,0.6045238963881795,0.6604224790753288,0.6867940425872803,0.6673660930934486,0.9861094093435789,19.30573844909668,0.5928461177102208,0.5989964740981828,0.5868207785306231,21.062068939208984,0.6146123975559628,0.9860744015543459,0.9061070680618286,0.5929030077728963,0.6034672537149147,0.5827022718214429,0.9934613704681396,0.6139739745623625,0.9846115760756768,1.4325380325317383,0.5326888517072567,0.4991869918699187,0.5710110269695762,1.209513783454895,0.5274496278744829
+0,3534,0.987752274881161,0.7537264823913574,0.6567477223569509,0.648124191461837,0.6656038262255879,0.7020363807678223,0.6981410119922387,0.9867570534443914,24.352754592895508,0.6126562898698648,0.5892747576389741,0.6379699747575395,26.61234474182129,0.6450371585049556,0.9867595540007652,1.1376570463180542,0.6125394677492105,0.5947197197197197,0.631460077055932,1.252740740776062,0.6450244255385844,0.9855317808212327,2.2027506828308105,0.5697318007662836,0.548506086315013,0.5926664009565564,1.9296152591705322,0.5787703066860371
+0,4712,0.9876897609718163,0.7565015554428101,0.6575841285786038,0.6233781692655637,0.6957619237411984,0.6885451078414917,0.6990351355828277,0.9868620768120907,28.162517547607422,0.6208916368369671,0.6085736157182955,0.6337186129932244,30.690998077392578,0.6546793227749903,0.9868320701356051,1.3165278434753418,0.6182936991218512,0.5973495169680456,0.6407599309153713,1.456634759902954,0.6524666948983449,0.9849416495170176,3.009805202484131,0.5610597658656807,0.5231529357692749,0.6048890660289624,2.563816547393799,0.5602173653734028
+0,5890,0.988404920094721,0.7338276505470276,0.6742635157008742,0.6576155594847184,0.6917762720871529,0.6837186813354492,0.7269523922073817,0.9875922392732382,33.246795654296875,0.6446611652913228,0.608808596056205,0.6850006642752757,36.723472595214844,0.6918381876316712,0.9876822593026948,1.5615947246551514,0.6437823834196891,0.6280803740679893,0.660289624020194,1.7061346769332886,0.6924018048593876,0.9860668998852244,3.684500217437744,0.6004448681283763,0.5755360623781677,0.6276072804570214,3.2909727096557617,0.6153208051484209
+0,7068,0.9887650002125473,0.7390127778053284,0.6837673781084785,0.6720554272517321,0.6958947787963332,0.704119086265564,0.7435809632681054,0.9878823038125983,33.56936264038086,0.6525974025974027,0.6647374948325755,0.6408927859705061,36.4136962890625,0.7043954622209831,0.9879023082635886,1.573347806930542,0.6516363636363636,0.6485917346670176,0.6547097117045304,1.734956979751587,0.7043861492514139,0.9859868820812631,4.364479064941406,0.5893384040390794,0.5818228896944588,0.5970506177760064,3.8188748359680176,0.6135671399227125
+0,8246,0.9888125107836494,0.7509059906005859,0.692441747886142,0.6733617875972885,0.712634515743324,0.7037396430969238,0.7475421250658818,0.98819987447207,36.8409423828125,0.6641519601239392,0.6735892881541194,0.6549754218148001,39.23794174194336,0.7175325887014649,0.988284893388779,1.731938123703003,0.6633084827725165,0.6707416462917686,0.6560382622558788,1.8434001207351685,0.7169166764161801,0.9859793804121417,4.958352565765381,0.5974854808858255,0.5749201670351265,0.6218945130862229,4.391791820526123,0.6142027306709317
+0,9424,0.9887049868595763,0.7322006225585938,0.6862444017914267,0.6618536344563741,0.7125016606881892,0.6807997226715088,0.7443829209484345,0.9882498855995459,40.079715728759766,0.6707542194092826,0.6657505562099202,0.6758336654709711,43.07021713256836,0.723885279932281,0.9882698900505362,1.8434743881225586,0.6704774714189643,0.6788778428435245,0.6622824498472167,2.0096449851989746,0.7238721118433815,0.9859893826376369,5.380288124084473,0.6054014420139313,0.56047064147528,0.6581639431380364,4.615057945251465,0.6196362628465429
+0,10602,0.9893551315167625,0.703508734703064,0.7015535568274734,0.6661490683229814,0.7409326424870466,0.6501141786575317,0.7619187656364448,0.9886624774012218,42.9025993347168,0.681393943463372,0.6888406190605485,0.6741065497542181,45.32282638549805,0.7356920434793855,0.988719990197819,1.982519268989563,0.6792032499017167,0.670071105365223,0.6885877507639165,2.1548962593078613,0.7351743715191665,0.9866120211747114,5.246329307556152,0.621568142468464,0.5813765182186235,0.6677295071077455,4.622967720031738,0.6442855756182917
+0,11780,0.9894951626736949,0.7134639024734497,0.7080015663751469,0.695830660679923,0.7206058190514149,0.6776121854782104,0.7662360217412889,0.989107576435757,43.47560501098633,0.6944265671257562,0.67344900761453,0.7167530224525043,46.31974411010742,0.7512582066816174,0.9890950736538879,2.0475521087646484,0.6936112979152657,0.7023015116437423,0.6851335193304106,2.1353759765625,0.7504673451060648,0.9870596207656204,5.579667091369629,0.6318537859007832,0.6368421052631579,0.6269430051813472,5.124835968017578,0.660836404608483
+0,-1,0.9895176676810591,0.7127859592437744,0.7088297803825595,0.687875,0.7311013684070679,0.6725353002548218,0.766883015507178,0.9891250803303735,43.52593994140625,0.6948181697082723,0.6966742353412582,0.6929719675833665,45.62451934814453,0.7515727926013045,0.9891025753230094,2.034733533859253,0.6941492938802959,0.7028462481274683,0.6856649395509499,2.1360626220703125,0.7508375610140123,0.9870796252166107,5.5805463790893555,0.6328877005347594,0.6368895466164401,0.6289358310083699,5.118690490722656,0.6615855674100193
+1,1178,0.9894951626736949,0.7041952013969421,0.709255138107082,0.6990065797961553,0.7198086887206058,0.653529167175293,0.7681206666093858,0.9888725241366204,45.376976013183594,0.6838216230230749,0.6676370079736742,0.7008104158363225,48.172645568847656,0.7417265062262228,0.9888275141218921,2.1343140602111816,0.6814107937326714,0.6619894763217239,0.7020061113325362,2.271970748901367,0.739865051934673,0.9873996964324562,5.535214424133301,0.644778429981294,0.626629889669007,0.6640095655639697,4.9561896324157715,0.6809223324031002
+1,2356,0.9894651559972094,0.6965053081512451,0.7090958019375673,0.7182772250238517,0.7001461405606483,0.6739426255226135,0.7683052720541128,0.9891100769921307,44.86609649658203,0.6960184271141823,0.6896191966614502,0.7025375315530756,48.21609115600586,0.7533748490714023,0.9890950736538879,2.120091199874878,0.6964663631116527,0.6731961319117282,0.721402949382224,2.296689987182617,0.7539451088830095,0.9868620768120907,5.682197093963623,0.6382841684915626,0.6194524315539442,0.6582967981931712,5.196109771728516,0.6617863773556443
+1,3534,0.9898052316640452,0.6993827819824219,0.7178254190876913,0.7217297878055332,0.7139630662946725,0.6562600135803223,0.7785936335773289,0.9891475853377376,45.74395751953125,0.6928543739501227,0.6743805810589862,0.7123688056330544,48.87615203857422,0.7492569851012325,0.9891525864504852,2.132749557495117,0.6909622930105738,0.6917443408788282,0.6901820114255347,2.2733407020568848,0.7476903190210943,0.9879273138273266,5.527857780456543,0.6584126156653198,0.6461184294666837,0.6711837385412515,5.005368232727051,0.6951980108965281
+1,4712,0.9899877722793321,0.6983892917633057,0.7215493145214961,0.7228963861848247,0.7202072538860104,0.6632986068725586,0.7814749906045708,0.9891000747666355,44.39826965332031,0.6885550977003855,0.6889213991222237,0.688189185598512,46.871482849121094,0.7493853841724055,0.9891225797739998,2.0823020935058594,0.6884342495005855,0.7148783977110157,0.6638767105088349,2.172579050064087,0.7492157125603809,0.9875422281457624,5.5100836753845215,0.6489782679208563,0.6341277890466531,0.6645409857845092,4.896665096282959,0.6820997693317946
+1,5890,0.9897177121909625,0.6991806626319885,0.7207160461797899,0.7040932708148524,0.7381426863292149,0.6669066548347473,0.7800048565592568,0.9891650892323542,45.411197662353516,0.6965709728867623,0.6968488232947746,0.6962933439617377,48.16046142578125,0.756201350887365,0.9891600881196067,2.157766342163086,0.6978585334198573,0.6821007230749715,0.714361631460077,2.29060697555542,0.7568554454731174,0.9874947175746603,5.884613990783691,0.6447028423772609,0.6274361876021627,0.6629467251228909,5.367840766906738,0.6799089878972713
+1,7068,0.9901278034362646,0.691852867603302,0.7241709794901284,0.697562776957164,0.7528895974491829,0.6407358646392822,0.7889780304870939,0.9894076432006121,46.45985412597656,0.7043466559009555,0.7135650988411725,0.6953633585757938,49.46348190307617,0.7651871902709004,0.9894101437569859,2.1956400871276855,0.7034464333422389,0.7073203492276696,0.699614720340109,2.342211961746216,0.7644801699810277,0.9881698677955845,5.858129501342773,0.6723883942868123,0.6491466732624289,0.6973561844028165,5.204281330108643,0.711156966303491
+1,8246,0.9899752694974632,0.6938679814338684,0.7223382045929019,0.709652608639918,0.7354855852265179,0.6544907093048096,0.7830271309222359,0.9894001415314908,47.069664001464844,0.7029310456879184,0.6880407124681934,0.7184801381692574,50.715579986572266,0.7615763378432447,0.9894151448697335,2.2189149856567383,0.7028257667068435,0.7085189685432699,0.6972233293476817,2.3528032302856445,0.7619977266421913,0.9879198121582052,6.060050010681152,0.6613897359371959,0.6463352777073295,0.6771622160223196,5.476638317108154,0.6961943552317517
+1,9424,0.9897377166419529,0.6783279776573181,0.7202190170940173,0.7239897972882267,0.7164873123422346,0.6514522433280945,0.7802359579851517,0.9891550870068591,47.5714111328125,0.7007757902160672,0.6771995043370508,0.7260528763119437,51.352176666259766,0.7568726544317298,0.9891525864504852,2.250195026397705,0.6976683087027915,0.6899194595998961,0.7055931978211771,2.3942863941192627,0.7559439645956729,0.9876622548517046,5.836494445800781,0.6533438860308667,0.6487229862475442,0.6580310880829016,5.381386756896973,0.6862375047562689
+1,10602,0.9900627889705459,0.68120276927948,0.7256444700313439,0.699728596101653,0.7535538727248572,0.631742537021637,0.7895619607085272,0.9893651337422577,49.59700012207031,0.7034473837397321,0.6854045878497605,0.7224657898233028,52.31041717529297,0.7630108806643472,0.9893201237275294,2.2681407928466797,0.7035261671810362,0.6955336276291872,0.7117045303573801,2.441592216491699,0.7635488587620093,0.988164866682837,5.982782363891602,0.6654709711704531,0.6654709711704531,0.6654709711704531,5.503890037536621,0.7070770181678924

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a245df89b4d2679cab722094dd81f2af87cb9a1a5526c1a3fb1e6e4ddaf889eb
+size 1112244081

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
+size 17082913

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "models/multi-qa-mpnet-zh/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}