Add new SentenceTransformer model.

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* 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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 256, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99670fac112e10d818351baf693284976186d6d6e0ad4394be4ca806a9d76a7f
+size 788519

README.md

@@ -0,0 +1,87 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 256 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)
+```
+
+
+
+## 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 11 with parameters:
+```
+{'batch_size': 15, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 5,
+    "evaluation_steps": 1,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 6,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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})
+  (2): Dense({'in_features': 768, 'out_features': 256, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.16.2",
+    "pytorch": "1.10.0+cu111"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,61 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,1,0.29738159236885175,0.4043406806151348,0.3024751811545745,0.37382440283286045,0.34415458154004197,0.4157842847834876,0.6526780680194606,0.7883371760420866
+0,2,0.3031624283631789,0.4043406806151348,0.3063872574246541,0.37382440283286045,0.3468390097109744,0.43358544682314765,0.6524461638210243,0.7883371760420866
+0,3,0.3308686415429029,0.47173079405099055,0.3317033289712859,0.4170557963577491,0.36844401073225047,0.46028718988263767,0.649524083572255,0.7883371760420866
+0,4,0.40395061881095135,0.5454784653581536,0.38865946830340165,0.4501150972885462,0.41642762858928484,0.49970404868474205,0.6462118438493869,0.7349336899231066
+0,5,0.4690692636015163,0.6421133450020222,0.4261379328804661,0.517505210724402,0.4450992418572448,0.5098761412788335,0.6164959778813233,0.718404039457708
+0,6,0.5791958270092159,0.6866162501011722,0.5558189908870489,0.5798092778632121,0.5487493810448505,0.5670941621205978,0.3917783770867643,0.5264057917442321
+0,7,0.510566081904828,0.6739011343585579,0.5316794464392648,0.6573714838931594,0.5226629009112731,0.6484709028733293,0.35744650840656694,0.5416639306353692
+0,8,0.4443079914029197,0.6344842755564536,0.46827126769587707,0.5899813704573036,0.4606183740862636,0.5620081158235521,0.34577712395328614,0.5098761412788335
+0,9,0.34594114917243524,0.5213197454471864,0.40695225907114013,0.5213197454471864,0.40457579877748406,0.5047900949817878,0.19014969255461509,0.3496656829218933
+0,10,0.214853163234958,0.25430231485228605,0.3657876873610591,0.42722788895184055,0.3674871146832529,0.42977091210036333,-0.15735148830508822,-0.2682889421691617
+0,11,0.20740278836911152,0.24667324540671745,0.3741452792515685,0.44757207414002337,0.3746461436966742,0.4882604445163891,-0.29174997403787717,-0.32042091671388034
+0,-1,0.20740278836911152,0.24667324540671745,0.3741452792515685,0.44757207414002337,0.3746461436966742,0.4882604445163891,-0.29174997403787717,-0.32042091671388034
+1,1,0.21195227269086533,0.2949906852286518,0.3668300212223982,0.5086046297045721,0.36395699921602276,0.5314918380412778,-0.36634435751159594,-0.32296393986240324
+1,2,0.2129577525577658,0.32296393986240324,0.3570662466574941,0.4806313750708206,0.352772454584097,0.5035185834075263,-0.41868246318031416,-0.4157842847834876
+1,3,0.20293618800348423,0.32296393986240324,0.3419572681163655,0.4806313750708206,0.3372610441731936,0.481902886645082,-0.4474005812901089,-0.5060616065560491
+1,4,0.17144181344932358,0.30261975467422036,0.31052993473368584,0.4412145162687163,0.3076937086463892,0.455201143585592,-0.45132747044250165,-0.4704592824767292
+1,5,0.14026909929533404,0.30261975467422036,0.27343917064162243,0.3789104491299062,0.27340116543850923,0.4348569583974091,-0.4214408431992714,-0.3878110301497362
+1,6,0.13454997172365227,0.2822755694860375,0.2457614332889927,0.42849940052610197,0.24688824937419793,0.4539296320113305,-0.3648451590160225,-0.27718952318899176
+1,7,0.1331087110950763,0.345851148199109,0.23642577568955542,0.46155870145689915,0.23959367144640473,0.44757207414002337,-0.26347993342233444,-0.12842266900040444
+1,8,0.13032848933801877,0.4259563773775791,0.22876740369755144,0.48317439821934344,0.23535124017627,0.48444590979360486,-0.12748764441984117,0.1436808078915416
+1,9,0.11913817418720092,0.3839964954269519,0.2243350534651157,0.4590156783083763,0.23390496284877504,0.4806313750708206,-0.13195079706887594,0.02924476620801289
+1,10,0.09908620780621555,0.29244766208012896,0.21184576412439243,0.4590156783083763,0.22340873546624357,0.45265812043706916,-0.1504188036494243,-0.03941685880210433
+1,11,0.10138695661506811,0.31787789356535756,0.20575075156909073,0.4590156783083763,0.21855457228885938,0.45265812043706916,-0.11363359592272457,0.024158719910967172
+1,-1,0.10138695661506811,0.31787789356535756,0.20575075156909073,0.4590156783083763,0.21855457228885938,0.45265812043706916,-0.11363359592272457,0.024158719910967172
+2,1,0.10867633791806154,0.35093719449615474,0.21099676265373304,0.4590156783083763,0.2241232636291513,0.49588951396195774,-0.10808401211745591,0.06230406713881007
+2,2,0.11741482095041503,0.39035405329825906,0.2194488313638225,0.4590156783083763,0.23193273735549827,0.49588951396195774,-0.11155469427645483,0.045774416673411485
+2,3,0.12690623354373742,0.381453472278429,0.22396853819293433,0.48444590979360486,0.23584484802596112,0.5213197454471864,-0.07886137947041366,0.18182615511938452
+2,4,0.12933304881088992,0.381453472278429,0.22697508159942292,0.4806313750708206,0.23674997980816412,0.5213197454471864,-0.09351384507028047,0.1767401088223388
+2,5,0.12356234377761036,0.41196975006070335,0.22315724561316355,0.48444590979360486,0.2299074039866915,0.4984325371104806,-0.13863187134963048,0.1296941805746659
+2,6,0.11230042528498023,0.3789104491299062,0.21486702249380507,0.47300230562525203,0.2197463749379041,0.4806313750708206,-0.1972657347806303,-0.0673901134358558
+2,7,0.09858093046235299,0.32042091671388034,0.20428540441451176,0.4590156783083763,0.20743199881610835,0.4806313750708206,-0.25326113634636754,-0.1347802268717116
+2,8,0.08071875254453191,0.24158719910967172,0.1894780550485504,0.40179765746661195,0.19113703629921694,0.4361284699716705,-0.2957567988780469,-0.21869999077296598
+2,9,0.06421951768430245,0.2657459190206389,0.1751474992445138,0.3534802176446776,0.17593103378984887,0.38908254172399764,-0.3094294134371616,-0.25048778012950174
+2,10,0.04799988063577147,0.19708429401052166,0.16143814661840797,0.3661953333872919,0.16114118275761535,0.38526800700121333,-0.3199709970266754,-0.2225145254957503
+2,11,0.032980850476875434,0.17165406252529306,0.14817240376204094,0.31279184726831183,0.147006192188734,0.31787789356535756,-0.3275241536824916,-0.23904417596114885
+2,-1,0.032980850476875434,0.17165406252529306,0.14817240376204094,0.31279184726831183,0.147006192188734,0.31787789356535756,-0.3275241536824916,-0.23904417596114885
+3,1,0.018839929024558014,0.12079359955483586,0.1362965301229738,0.31279184726831183,0.13619499914433025,0.27846103476325323,-0.3276643854332726,-0.2250575486442731
+3,2,0.007996348788690714,0.12079359955483586,0.12722257392930164,0.31279184726831183,0.12894521904908324,0.27846103476325323,-0.32427736644923444,-0.24285871068393314
+3,3,0.002609164605006253,0.12079359955483586,0.12322377901997654,0.31279184726831183,0.12701165076233467,0.3038912662484818,-0.31725810264156834,-0.2250575486442731
+3,4,0.0028854026136120297,0.12079359955483586,0.12382902513402451,0.31279184726831183,0.12962679147789194,0.3394935903278018,-0.3054500843601638,-0.2225145254957503
+3,5,0.00046534944015256413,0.10680697223796014,0.12215075436346347,0.2988052199514361,0.12979898299248765,0.3534802176446776,-0.29367201529181475,-0.2225145254957503
+3,6,-0.0011606803961149354,0.09536336806960725,0.12214127507897475,0.32042091671388034,0.13117067756758732,0.3712813796843376,-0.28432542725440235,-0.18436917826790739
+3,7,-0.00044790379835103853,0.12842266900040444,0.12300107503627687,0.32804998615944897,0.13306458904853832,0.3878110301497362,-0.27296246630680554,-0.18436917826790739
+3,8,-0.0029680790543025267,0.14622383104006448,0.12023668726570516,0.32804998615944897,0.13044275006215988,0.3878110301497362,-0.2672300857152273,-0.19199824771347596
+3,9,-0.00580567178057294,0.12842266900040444,0.11772494684232321,0.32804998615944897,0.12696292862076292,0.3878110301497362,-0.2703290863711082,-0.20598487503035168
+3,10,-0.00030418375194096546,0.17928313197086163,0.12064225494489768,0.38526800700121333,0.1280487072192669,0.3878110301497362,-0.26784935792860504,-0.2250575486442731
+3,11,-0.00016725660603038705,0.14622383104006448,0.12027825810462753,0.38526800700121333,0.12604903120624197,0.3878110301497362,-0.27695668718411937,-0.25557382642654747
+3,-1,-0.00016725660603038705,0.14622383104006448,0.12027825810462753,0.38526800700121333,0.12604903120624197,0.3878110301497362,-0.27695668718411937,-0.25557382642654747
+4,1,0.0020573979465674957,0.17928313197086163,0.12100885560039151,0.4132412616349648,0.12522600390931263,0.3878110301497362,-0.28072083934903985,-0.25557382642654747
+4,2,0.0011191825774035855,0.17928313197086163,0.1201987542410544,0.4132412616349648,0.12342171986150025,0.3878110301497362,-0.28940949325052795,-0.25557382642654747
+4,3,0.003686788118831583,0.17928313197086163,0.1223887704706159,0.4132412616349648,0.1243204534008643,0.3878110301497362,-0.295728523949944,-0.24158719910967172
+4,4,0.006836749729132741,0.17165406252529306,0.12504839516917515,0.4056121921893962,0.1253641296730243,0.3878110301497362,-0.3014276296854272,-0.23014359494131884
+4,5,0.007548397237431492,0.13859476159449588,0.1260278349333132,0.4056121921893962,0.12489196436779082,0.3928970764467819,-0.3091173460466043,-0.25048778012950174
+4,6,0.007563665923617185,0.11316453010926729,0.1262682525133201,0.37763893755564476,0.12417387150620204,0.3928970764467819,-0.31459474157947565,-0.2581168495750703
+4,7,0.008413866109005163,0.11316453010926729,0.12692990085424716,0.37763893755564476,0.1244159429628407,0.3928970764467819,-0.31563960997414886,-0.2581168495750703
+4,8,0.00846880052113597,0.11316453010926729,0.12692955056226216,0.37763893755564476,0.12433608784654811,0.3928970764467819,-0.31472258812183646,-0.25048778012950174
+4,9,0.008984460552752744,0.13859476159449588,0.1273626118388567,0.4056121921893962,0.12476588605115743,0.3928970764467819,-0.31320989958493434,-0.25048778012950174
+4,10,0.009114622503107413,0.13859476159449588,0.12753988587933993,0.4056121921893962,0.12496282604202841,0.3928970764467819,-0.3126021176400818,-0.25048778012950174
+4,11,0.009139842638446213,0.13859476159449588,0.12759477143182116,0.4056121921893962,0.12507514349860954,0.3928970764467819,-0.3123428340299642,-0.25048778012950174
+4,-1,0.009139842638446213,0.13859476159449588,0.12759477143182116,0.4056121921893962,0.12507514349860954,0.3928970764467819,-0.3123428340299642,-0.25048778012950174

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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c444eaba015685d9b72f257b54ca4cdf4d25766e3277abc803efcadad6bc183
+size 669506993

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.7703289359007985,0.42595603936918564,0.7810694081911008,0.4411826839933626,0.7813644638049656,0.453809261232408,0.7830485034558546,0.4436364975880806

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-uncased", "tokenizer_class": "BertTokenizer"}