Upload with huggingface_hub

1_Pooling/config.json

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

README.md

@@ -0,0 +1,126 @@
+---
+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
+
+
+def cls_pooling(model_output, attention_mask):
+    return model_output[0][:,0]
+
+
+# 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, cls pooling.
+sentence_embeddings = cls_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 18092 with parameters:
+```
+{'batch_size': 64, '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': 'dot_score'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 1000,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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 +1,24 @@
+{
+  "_name_or_path": "weights_weights_microsoft/mpnet-base",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.22.2",
+    "pytorch": "1.12.1+cu102"
+  }
+}

eval/similarity_evaluation_dev_results.csv

@@ -0,0 +1,87 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,1000,0.6771242823147795,0.6764832914917542,0.659498331344462,0.6761612599127045,0.6582750489154041,0.6756293659921812,0.6514607911672344,0.6563172443393622
+0,1000,0.6762047805215603,0.6773068370670591,0.6598617332937724,0.6764468121156492,0.6587554236199218,0.6760944152729468,0.6479805084820658,0.6523816276875323
+0,2000,0.6816379851987073,0.6813836116301402,0.6651122926426283,0.6800492014860166,0.6631384429395051,0.6787374537425808,0.6588121208711843,0.6625608048270323
+0,3000,0.6856255497333759,0.6863027277591326,0.66843421640015,0.6855614546602602,0.6674481591312561,0.6852609650720887,0.6568919412010155,0.6621247588634765
+0,4000,0.6842525262013807,0.683378493891458,0.6664716041324972,0.6827336910563004,0.6651089777075586,0.6820501830851377,0.6585655194842882,0.662020695370972
+0,5000,0.678448957830625,0.6788136415822063,0.6615424021071817,0.6777430000847317,0.6599088337720908,0.6765089265552817,0.6574793482107355,0.6622940488230795
+0,6000,0.6824303097720801,0.682497937426339,0.6648842545242759,0.681527625018098,0.6637861889162625,0.6810106684687532,0.6612257421018438,0.667849620248544
+0,7000,0.6871062560877037,0.687416431193572,0.6690982213646153,0.6870367662594128,0.6680636473060342,0.6866279809587558,0.6583344579947678,0.6633310738226418
+0,8000,0.6894718198286416,0.6886493844777327,0.6726257982981568,0.6884846927567461,0.6712198232647864,0.6874453026183552,0.6558968627902816,0.6596274840125335
+0,9000,0.6885692639426904,0.6881166192201538,0.6712661019636053,0.6871724471576166,0.6696166139040619,0.6859172124334183,0.66376126094342,0.6687959008862147
+0,10000,0.6856428479913557,0.685823488011014,0.6674465913984942,0.6841712858771556,0.6660423371376175,0.6833457486786937,0.6592964093121516,0.664191589254521
+0,11000,0.6905849382283602,0.6932873052095392,0.671916181496984,0.6922874914721558,0.67039971721757,0.6915040278051682,0.6640851146785033,0.6710338884053102
+0,12000,0.6888370901408007,0.6891698264267835,0.671074282276042,0.687416174812525,0.6699153456174107,0.6867153644322708,0.6666476593385049,0.6730667363809026
+0,13000,0.6904382773179654,0.6906089150397164,0.6717105295030468,0.6896251589616587,0.6700006932557472,0.6884316652153556,0.6636910523620839,0.6689710412650953
+0,14000,0.6881509866054158,0.688300224013324,0.6703852050425845,0.6871580077115539,0.6688728462477451,0.6862361246613933,0.6600665147547357,0.6666837605672329
+0,15000,0.6950730820775312,0.695993204987069,0.6755716000851062,0.6946070119632027,0.673300534526808,0.6930429476483158,0.667350568470686,0.6759853687664313
+0,16000,0.7054967815158681,0.7033131258319401,0.6864182475955567,0.7028379861618128,0.6850059805077626,0.7018271014398972,0.6734487458011355,0.6802679052085355
+0,17000,0.6980147496622318,0.6979013261488017,0.6808450075113968,0.6972451957824174,0.6791376483803483,0.6960936511183841,0.6649025195107074,0.6712529694832083
+0,18000,0.7009202975562503,0.7005149878573765,0.6820477989278442,0.7004475132605037,0.6805477161418124,0.6997149610535809,0.6661704264269532,0.6727128458059449
+0,-1,0.692397640846877,0.693649784735138,0.6732754000657764,0.6919606126050587,0.6716559389496284,0.6909346660899567,0.6697510988478631,0.6763647773031198
+1,1000,0.7015239394042643,0.7015240054365504,0.6828640642792396,0.7009626026557895,0.681593613847875,0.7002100094987335,0.6657633659877792,0.6733293847243035
+1,2000,0.7045768568000108,0.7036172251674683,0.6854893172478715,0.7033256904130204,0.6839202591602107,0.7025195717750456,0.6688618245356542,0.6755921431870937
+1,3000,0.7002463240617335,0.6996794924633146,0.6814472157248276,0.6992286260302865,0.679422106359481,0.6979158825201447,0.664458613613206,0.6702329978421663
+1,4000,0.706230926372149,0.7055620673850997,0.6878080137367049,0.7054174164011954,0.6862758100718989,0.704549058860674,0.6649872532595464,0.6730911340281076
+1,5000,0.7072384078282561,0.7054700783443069,0.686574699233261,0.7051766762293704,0.6846941378851968,0.7042074915770826,0.6724440068180834,0.678268666172432
+1,6000,0.7062319400652455,0.7039650164053173,0.6867146609119006,0.7033050271165022,0.6850365167024013,0.7022550563314064,0.673381571739164,0.6790415492581303
+1,7000,0.7092825293930414,0.7073627641213579,0.69016385298173,0.7073022602105401,0.6884838259971511,0.7063614565252695,0.6690409162985401,0.6750394615493018
+1,8000,0.7174608804381496,0.7156141527645704,0.698221310000291,0.7147955785666942,0.6966479745761167,0.71410049421125,0.681918617543596,0.6882730764907438
+1,9000,0.7095817226708898,0.7080050698847309,0.6880288012418445,0.706219551776338,0.6863259361699865,0.7053526879126626,0.6789059215622656,0.6853530747933163
+1,10000,0.7046879802736112,0.704398323806573,0.6859241032719507,0.7029801398522112,0.6836957640204047,0.7014361164449793,0.6689935517622023,0.6768343077842148
+1,11000,0.6992693690166031,0.6995445584588277,0.6795023924920787,0.6979752584463644,0.6776549889685164,0.6968204773153437,0.6690661076340341,0.6769047622402233
+1,12000,0.7041632433348246,0.7033710079813245,0.6851316777916469,0.7025103604132158,0.6829555385604473,0.7012047121556387,0.6692504901618795,0.6759085659532239
+1,13000,0.7115371127744088,0.7097982980356558,0.6924583303886527,0.7093690906550363,0.6907438539855795,0.7083777489286693,0.6800021651602721,0.6862649995533213
+1,14000,0.7125291699421366,0.7120674049880338,0.6925526014149266,0.7112107406317314,0.6907724200747138,0.7098804456999981,0.6794266510483311,0.6872401591510287
+1,15000,0.7048008612027256,0.7064030397905715,0.6853591766141682,0.7044960312768619,0.6829082827618137,0.7027929251469164,0.6754063693152729,0.6839316620190965
+1,16000,0.7127347698737073,0.7114233565201366,0.6933169574772103,0.7102709327982939,0.6914182966899227,0.7090937456085837,0.6745257188701042,0.6818388158252124
+1,17000,0.7096405848644866,0.7083213681658052,0.6905405764764077,0.7072715141929011,0.6894157984424184,0.7065257673038561,0.6739102312239496,0.6823174331206286
+1,18000,0.7106980182707022,0.7094333288952651,0.6911414070594157,0.709261541767322,0.6895648668014576,0.708172236006444,0.6675439560478471,0.674544786485046
+1,-1,0.7018505764235614,0.7024458885396555,0.6826001933549382,0.7014966126861849,0.6812479368674255,0.700669332811591,0.661439329057919,0.668832995384463
+2,1000,0.7237030464232489,0.7210346658707086,0.7052917670972099,0.7218981609855295,0.7038803532194167,0.7211409621034048,0.6711313439639994,0.6778617480835146
+2,2000,0.7152547247776971,0.7147133064488497,0.696922653096234,0.7141385844080866,0.6954208876691186,0.7133033379502887,0.6747812338565775,0.682610951891035
+2,3000,0.7153996586676451,0.7146618970910537,0.6961358762478527,0.7139894599287361,0.6937676801341025,0.7123434891811011,0.6726644473082177,0.680230935283563
+2,4000,0.714685205341123,0.713670679860717,0.6954103826427915,0.7129060046129874,0.6935185902696785,0.7115262919988401,0.6737901954594521,0.6815283680238428
+2,5000,0.7223595108235663,0.7206349674055911,0.703071243045795,0.7206363288485639,0.7010223890083358,0.7193011792946856,0.6787750610636554,0.6870510773208861
+2,6000,0.708858313062525,0.708371532744964,0.6904024196086376,0.707383917688383,0.6890873074850346,0.7068648450158911,0.6692168090703918,0.6780403738014505
+2,7000,0.7210861030857394,0.7194903934175632,0.7029439013784191,0.719305660497738,0.7014001221375665,0.7184602068551926,0.6777737457423821,0.6854126996751758
+2,8000,0.7168043307186197,0.7152621293216855,0.6987826310537038,0.7156255969542645,0.6972821991035647,0.7147172820057085,0.6708059339672687,0.677946268565528
+2,9000,0.7223028245708996,0.7207863325321825,0.7034483656122903,0.7206144207447523,0.7019480836424291,0.7197151926655787,0.6776526099552802,0.6836837021740421
+2,10000,0.7234432696342937,0.7207986557819492,0.705229748791109,0.7214977156428131,0.7034055186049168,0.720412517651671,0.6785451311638433,0.6848256620228496
+2,11000,0.7166038684017262,0.714343980597503,0.698513077731165,0.7141501608784147,0.6965178255618713,0.712879615349711,0.6785387126366449,0.6846593596412894
+2,12000,0.7165258176752064,0.7152835396163237,0.6989897991611829,0.7168813296610216,0.6972908403530991,0.7158226454252907,0.6614851033598612,0.6678231063959152
+2,13000,0.7184668288821026,0.7181291035271137,0.699369377415503,0.7172363405104479,0.6970149412709927,0.7155048534275784,0.6735888771784229,0.6828747205220264
+2,14000,0.7242888880042018,0.7217529031014137,0.706253849939917,0.7222353714563615,0.7049800423530165,0.7213490890749127,0.6743805107399117,0.6831877823306493
+2,15000,0.7256827758270623,0.7241168622297859,0.7056560128398025,0.7228181768383448,0.7036680651352714,0.7213396287720594,0.6848678621628985,0.6935575351036504
+2,16000,0.7203423335364871,0.7197102213839013,0.70191514391553,0.7188523121076233,0.6998402622121591,0.7173580798454168,0.6698592350948372,0.6794407497195413
+2,17000,0.7195961719656683,0.7175390784375316,0.7002373306098935,0.7167854816922354,0.6984626426916105,0.715521782416887,0.6754844876206767,0.6836697606256471
+2,18000,0.7206175572775462,0.7183534126086077,0.7021557018548461,0.7180163187972838,0.7005899884810523,0.7170344374173666,0.6794698300011923,0.6865728333196571
+2,-1,0.7199805425708737,0.7182729999231608,0.7017718553543786,0.7175843806141813,0.699677604660226,0.7162090247106943,0.6783856449396246,0.686461799066889
+3,1000,0.7188163317408387,0.7171751051780674,0.6991936948357723,0.7160463321589147,0.6969481058642163,0.7145931775767306,0.675608487211426,0.6851738265744944
+3,2000,0.7221413900652955,0.719638895567875,0.7030821040879076,0.7195808810518705,0.7011625505921391,0.7183546496570181,0.6725339065359242,0.681343642987936
+3,3000,0.7307873175105782,0.7274559809145538,0.7117626206796147,0.7272352737767525,0.709575587715902,0.7257964341781493,0.6794840998546317,0.6883304607289454
+3,4000,0.7233444426362448,0.7204165087397373,0.7030247223202344,0.719308523503237,0.7011109831996134,0.7180799270143247,0.6822386663151632,0.6901907823179917
+3,5000,0.7255120391749064,0.7230809574167885,0.7058933804941857,0.7221689002777529,0.7032020513811231,0.7202589119692651,0.6788717727593826,0.6875019361085114
+3,6000,0.731696355696863,0.7276975924780752,0.7120873025448787,0.7276222754514687,0.7099063660508995,0.7261046413362708,0.6831432598584388,0.6910505509237871
+3,7000,0.727187626793385,0.724627594890672,0.7081280457498099,0.7243517441051839,0.7063660401771703,0.7233424775659971,0.6803966736935505,0.6879039995742555
+3,8000,0.7180355492087489,0.7169293858454756,0.6977667899562502,0.7162024273693817,0.6962910414860544,0.7152237824576413,0.6796266308800987,0.687066263564021
+3,9000,0.7247219688025189,0.721413576414975,0.7049807058422859,0.7202744717020859,0.7027715370283937,0.7186985819620056,0.6805133925072997,0.6893761992603772
+3,10000,0.7209579504253526,0.7186364753297247,0.7022742574013832,0.7184823639000861,0.6999368057394437,0.7167090522700131,0.6770030246047445,0.6855575919063723
+3,11000,0.7283508321642056,0.7257604679449561,0.7098819271210017,0.7257663105206161,0.7074515378670738,0.7239812979566707,0.675916043419123,0.6858793671652827
+3,12000,0.7254155982137053,0.722606447843735,0.7065341997495886,0.7226444057127437,0.7042284578922238,0.7210222102372121,0.6747666273114772,0.6837207965629394
+3,13000,0.723454464793881,0.721336898036105,0.7059413167626383,0.7215058067185843,0.703642411498135,0.7198539854823393,0.6768511503023149,0.6861925534097574
+3,14000,0.7233686521237327,0.7218002046749908,0.7049140596100067,0.7216336454687319,0.7026774645497598,0.7199108718655318,0.6753894416039223,0.6852965617602331
+3,15000,0.7290927353272858,0.72587872188609,0.7100750511778631,0.725790957122612,0.7077354777407661,0.7240759011469756,0.6812416313755426,0.6897877230154204
+3,16000,0.7252851685148058,0.7230454812255733,0.7056673723238882,0.7228773038230647,0.7036650368008485,0.7214899980300385,0.6790380890545302,0.6895100129478133
+3,17000,0.7251809152759146,0.7230395063175776,0.7057732035976054,0.7215104123847945,0.7032339364561462,0.719621585298263,0.6844629046804587,0.694222993795534
+3,18000,0.726718651036098,0.7242743267128805,0.7070476814173577,0.7235311860056427,0.7047500761445191,0.7220606045373231,0.6824199140622108,0.6925602184745273
+3,-1,0.7211565414134666,0.7196101411519771,0.7023951219439681,0.7192349570571422,0.6996508304045436,0.7173148860563463,0.6726180467602966,0.681527247709196
+4,1000,0.7322371206283487,0.728141355988751,0.7141241460191059,0.7290662186572294,0.7117012739003337,0.7273222837878626,0.679476074777345,0.6875311883359848
+4,2000,0.7348824811582444,0.7306192123625864,0.7177912641461932,0.7315958577653765,0.7152633535873811,0.7297322997295627,0.6817515384026174,0.6893854105659535
+4,3000,0.7309762825629159,0.7268935899401994,0.7130550418863335,0.7268445377661591,0.7112018774033015,0.7255728719517647,0.6800175809825002,0.6888385794031245
+4,4000,0.7322578296795372,0.7280753827802346,0.7139345234687549,0.7274880883304499,0.7118353394367034,0.7260015737104578,0.6879417095920579,0.6960553079362292
+4,5000,0.7284753625950682,0.7253749599708355,0.7096610543086577,0.7258001684844416,0.7071985516993327,0.7239230423317452,0.6744047207711916,0.6827717772885322
+4,6000,0.7294009916864721,0.72620037267164,0.7107945582556685,0.7264213130186312,0.7085873826193883,0.7249280765793251,0.6806735698114238,0.6892992718855602
+4,7000,0.7291302578599461,0.7252462498447685,0.7102735865590859,0.7255213380870872,0.7083100317228045,0.724295978037515,0.6778024411423031,0.68675606476029
+4,8000,0.735108687443278,0.7305846075313093,0.7167155134489289,0.7307583707060524,0.7147144110055865,0.7294508552674238,0.6838228204521622,0.6922364515417535
+4,9000,0.7306972525366605,0.7266369165403728,0.7116705501404859,0.7270882654358811,0.7095143304219935,0.7258442336625822,0.6763986548717984,0.6859998616796291

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 sha256:9cb2970adfe09f0569da88f8d69e1627f7d4be7193ac383e56e2ddc56ea2a409
+size 438014769

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "weights_weights_microsoft/mpnet-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}