commit 8fd37ebcc7aa0362ef34f58dba6cd00f9338284c Author: ModelHub XC Date: Wed May 13 18:19:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jfarray/Model_paraphrase-multilingual-MiniLM-L12-v2_10_Epochs Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d91d44 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,30 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz 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 +unigram.json 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 diff --git a/1_Pooling/config.json b/1_Pooling/config.json new file mode 100644 index 0000000..d1514c3 --- /dev/null +++ b/1_Pooling/config.json @@ -0,0 +1,7 @@ +{ + "word_embedding_dimension": 384, + "pooling_mode_cls_token": false, + "pooling_mode_mean_tokens": true, + "pooling_mode_max_tokens": false, + "pooling_mode_mean_sqrt_len_tokens": false +} \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e8a292 --- /dev/null +++ b/README.md @@ -0,0 +1,125 @@ +--- +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 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. + + + +## 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 + + + +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": 10, + "evaluation_steps": 1, + "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator", + "max_grad_norm": 1, + "optimizer_class": "", + "optimizer_params": { + "lr": 2e-05 + }, + "scheduler": "WarmupLinear", + "steps_per_epoch": null, + "warmup_steps": 11, + "weight_decay": 0.01 +} +``` + + +## Full Model Architecture +``` +SentenceTransformer( + (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel + (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) +) +``` + +## Citing & Authors + + \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..75d8c23 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 384, + "initializer_range": 0.02, + "intermediate_size": 1536, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 0, + "position_embedding_type": "absolute", + "torch_dtype": "float32", + "transformers_version": "4.16.2", + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 250037 +} diff --git a/config_sentence_transformers.json b/config_sentence_transformers.json new file mode 100644 index 0000000..b974b34 --- /dev/null +++ b/config_sentence_transformers.json @@ -0,0 +1,7 @@ +{ + "__version__": { + "sentence_transformers": "2.0.0", + "transformers": "4.7.0", + "pytorch": "1.9.0+cu102" + } +} \ No newline at end of file diff --git a/eval/similarity_evaluation_results.csv b/eval/similarity_evaluation_results.csv new file mode 100644 index 0000000..054deb8 --- /dev/null +++ b/eval/similarity_evaluation_results.csv @@ -0,0 +1,121 @@ +epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman +0,1,0.4106261751588814,0.41069823848644194,0.39567371234645116,0.4539296320113305,0.37736095233478156,0.4081552153379191,-0.05937455447312464,-0.24667324540671745 +0,2,0.41651035397112773,0.45265812043706916,0.3937387457625293,0.3878110301497362,0.3750556809078104,0.4081552153379191,-0.07328423584445982,-0.24667324540671745 +0,3,0.42157881063609787,0.46028718988263767,0.38691224392868884,0.4412145162687163,0.3670265583083535,0.4195988195062719,-0.0935159873529215,-0.18818371299069164 +0,4,0.4219259914762841,0.481902886645082,0.3761279511169032,0.40179765746661195,0.35561511251100175,0.40052614589235047,-0.11305814893721415,-0.20598487503035168 +0,5,0.4102992885751593,0.4933464908134349,0.36150098927587404,0.37763893755564476,0.34209274958274805,0.3712813796843376,-0.13025984799854368,-0.3051627778227432 +0,6,0.37651464126789436,0.41832730793201056,0.3421487981177414,0.33695056717927896,0.32434513916357155,0.3356790556050176,-0.14034304011710794,-0.3598377755159847 +0,7,0.32319127935624076,0.2733749884662075,0.3199151281004368,0.27591801161473034,0.30353717608186204,0.2746465000404689,-0.14656782947809885,-0.381453472278429 +0,8,0.2624759097672902,0.2695604537434232,0.293466480518489,0.22632906021853458,0.27689224229094295,0.23014359494131884,-0.15521023250898014,-0.37255289125859903 +0,9,0.18643805105274264,0.15639592363415591,0.2528034590438682,0.23014359494131884,0.23485887962601204,0.21742847919870456,-0.16834616110426084,-0.38653951857547475 +0,10,0.11969861937792727,0.0762906944556858,0.21017368838438502,0.14495231946580303,0.19251280144497956,0.11825057640631301,-0.1797115236720293,-0.3560232407932004 +0,11,0.06397899433131118,-0.01398662731687573,0.1608451180356569,0.10299243751517584,0.1426965836553944,0.054674997693241495,-0.18965318295799125,-0.3712813796843376 +0,-1,0.06397899433131118,-0.01398662731687573,0.1608451180356569,0.10299243751517584,0.1426965836553944,0.054674997693241495,-0.18965318295799125,-0.3712813796843376 +1,1,0.010524927836981104,-0.12842266900040444,0.09322474088304644,0.05086046297045721,0.0687045506580136,0.006357557871307151,-0.20240662763043885,-0.36365231023876904 +1,2,-0.017675961772208603,-0.13350871529745015,0.06825809478884814,0.00381453472278429,0.0453439602334941,-0.01398662731687573,-0.20164385468895424,-0.3331360324564947 +1,3,-0.03011421391073029,-0.23904417596114885,0.06173478972803007,0.01780116203966002,0.04087404127097281,-0.01398662731687573,-0.19789834409132298,-0.30261975467422036 +1,4,-0.027890767969658725,-0.2619313842978546,0.07637457985186541,-0.012715115742614302,0.0566883553316959,0.02924476620801289,-0.18963885028494126,-0.2873616157830832 +1,5,-0.04004376401195804,-0.3051627778227432,0.052706553489229625,-0.012715115742614302,0.029663850727734118,-0.01907267361392145,-0.19453584898133444,-0.2873616157830832 +1,6,-0.054372631887607464,-0.32296393986240324,0.02247690246879877,-0.08773429862403868,-0.00524840786148028,-0.09409185649534582,-0.20107794256711695,-0.2733749884662075 +1,7,-0.07327866796846358,-0.3115203356940504,-0.022142093756691142,-0.15893894678267878,-0.054659054116731505,-0.14113778474301875,-0.2071083550606776,-0.2593883611493318 +1,8,-0.08615159897809209,-0.28609010420882175,-0.05779091101643137,-0.15003836576284876,-0.09316134794260485,-0.14622383104006448,-0.2101161953789501,-0.2593883611493318 +1,9,-0.09594135008226419,-0.2682889421691617,-0.09448186712475778,-0.19581278243626024,-0.13550485109812388,-0.24285871068393314,-0.21155943968747729,-0.23141510651558028 +1,10,-0.09155295060443958,-0.18691220141643022,-0.10960095936041375,-0.1983558055847831,-0.16275986335424275,-0.24158719910967172,-0.21229822802333156,-0.2695604537434232 +1,11,-0.06187076481398492,-0.14495231946580303,-0.07699048000894976,-0.040688370376365766,-0.14098145542342583,-0.11570755325779014,-0.207119732562768,-0.2695604537434232 +1,-1,-0.06187076481398492,-0.14495231946580303,-0.07699048000894976,-0.040688370376365766,-0.14098145542342583,-0.11570755325779014,-0.207119732562768,-0.2695604537434232 +2,1,-0.03255777178281436,-0.07120464815864008,-0.03821893191136488,-0.045774416673411485,-0.10396620619854707,-0.12715115742614302,-0.19453286882237444,-0.2695604537434232 +2,2,-0.0032893430517299503,0.0025430231485228604,-0.0037618488660964176,-0.0012715115742614302,-0.06681662618022005,-0.02924476620801289,-0.1635004965638843,-0.22124301392148887 +2,3,0.015857113944296567,0.10299243751517584,0.01468550876839963,0.0025430231485228604,-0.04711612573177659,-0.022887208336705742,-0.12528874695801676,-0.19708429401052166 +2,4,0.015801689152062048,0.05086046297045721,0.013819213729611236,0.0025430231485228604,-0.04718522080113322,-0.03305930093079718,-0.10606256928859016,-0.19199824771347596 +2,5,-0.002340201329506811,0.031787789356535756,-0.0031865365029976754,0.0025430231485228604,-0.06662641683252482,-0.054674997693241495,-0.11980047365252748,-0.20852789817887454 +2,6,-0.011751455469205285,0.010172092594091442,-0.01645293838264101,0.0025430231485228604,-0.08143389224334845,-0.04450290509915005,-0.12317611357587267,-0.24667324540671745 +2,7,-0.022229406009818493,0.022887208336705742,-0.03059835089288744,-0.01907267361392145,-0.09580959332495027,-0.04450290509915005,-0.12535055637428008,-0.24667324540671745 +2,8,-0.03768783163248228,-0.010172092594091442,-0.0473104343466776,-0.01907267361392145,-0.11253422677485489,-0.06357557871307151,-0.13879926694053574,-0.2225145254957503 +2,9,-0.037379685660760026,-0.01780116203966002,-0.047916184386079884,-0.012715115742614302,-0.11402557074142765,-0.09663487964386869,-0.1390719346572019,-0.19199824771347596 +2,10,-0.03316019034943963,-0.022887208336705742,-0.04481329171666349,-0.012715115742614302,-0.11258195050833633,-0.10044941436665299,-0.14234738982418466,-0.2492162685552403 +2,11,-0.02090921349496955,-0.022887208336705742,-0.03671162286247917,-0.00890058101983001,-0.10767342236121023,-0.09027732177256154,-0.13775504773467426,-0.21615696762444314 +2,-1,-0.02090921349496955,-0.022887208336705742,-0.03671162286247917,-0.00890058101983001,-0.10767342236121023,-0.09027732177256154,-0.13775504773467426,-0.21615696762444314 +3,1,-0.030122638463459802,-0.022887208336705742,-0.04533236831524494,-0.01525813889113716,-0.11844494723012336,-0.09027732177256154,-0.1499540653357626,-0.25557382642654747 +3,2,-0.03499242416188924,-0.07247615973290152,-0.05024235187796268,-0.031787789356535756,-0.12544221028696645,-0.08137674075273153,-0.15899078667620253,-0.2581168495750703 +3,3,-0.030101684117309443,-0.07247615973290152,-0.045785087200671475,-0.03941685880210433,-0.12298045406208104,-0.09790639121813012,-0.16166421616490959,-0.2581168495750703 +3,4,-0.018392647109678795,-0.034330812505058615,-0.032226418955371344,-0.025430231485228605,-0.11189227141001606,-0.11697906483205156,-0.16125520486417927,-0.24285871068393314 +3,5,-0.004222040765444905,-0.05594650926750292,-0.01834463319642487,-0.025430231485228605,-0.09992655075021963,-0.09536336806960725,-0.16054618491455425,-0.24285871068393314 +3,6,0.015008641638438057,-0.05594650926750292,-0.002529281115247077,-0.011443604168352871,-0.08469469726888403,-0.08137674075273153,-0.16077857390784017,-0.24285871068393314 +3,7,0.042003149655349264,0.011443604168352871,0.018440906694661894,-0.0025430231485228604,-0.06371004944870552,-0.048317439821934344,-0.15898619500996042,-0.24285871068393314 +3,8,0.058220925311202286,0.05976104399028721,0.031108705009034145,0.05848953241602578,-0.048901448743304946,-0.03051627778227432,-0.160811640140161,-0.22887208336705742 +3,9,0.07471449254431813,0.0839197639012544,0.0478808176625412,0.08010522917847009,-0.028185808118208085,0.01652965046539859,-0.1618833557671143,-0.22887208336705742 +3,10,0.0770499175675193,0.09409185649534582,0.061250625063528234,0.08137674075273153,-0.008930482178091385,0.022887208336705742,-0.1650433190307382,-0.22887208336705742 +3,11,0.08141847750784448,0.057218020841764354,0.08128369302428537,0.10299243751517584,0.01688928208312896,0.0381453472278429,-0.16567436470071775,-0.20979940975313596 +3,-1,0.08141847750784448,0.057218020841764354,0.08128369302428537,0.10299243751517584,0.01688928208312896,0.0381453472278429,-0.16567436470071775,-0.20979940975313596 +4,1,0.07634485101964444,0.0025430231485228604,0.09555839623647985,0.09917790279239155,0.03823509146862936,0.052131974544718636,-0.1672462904458947,-0.20979940975313596 +4,2,0.06710933218878008,-0.026701743059490034,0.10605479473892146,0.09917790279239155,0.056359135182206394,0.05340348611898007,-0.1683273070174047,-0.20979940975313596 +4,3,0.07201727616873489,-0.026701743059490034,0.12741450169023305,0.15385290048563305,0.084122966378303,0.06484709028733295,-0.16661962653030254,-0.20979940975313596 +4,4,0.08052142602141382,-0.026701743059490034,0.1417967716420176,0.17038255095103164,0.10253183919296664,0.13350871529745015,-0.1645792451500799,-0.18182615511938452 +4,5,0.09626825736618978,-0.026701743059490034,0.16041344161542634,0.19199824771347596,0.12430637875216104,0.18055464354512307,-0.16103077311486624,-0.18182615511938452 +4,6,0.11357353705242959,-0.0012715115742614302,0.18320766950741413,0.19581278243626024,0.15007237443455354,0.18436917826790739,-0.1555555205037696,-0.16656801622824735 +4,7,0.13706492388894317,0.02797325463375146,0.20786959732118965,0.1780116203966002,0.17763802053717231,0.19581278243626024,-0.14897527830927423,-0.16656801622824735 +4,8,0.16035046385761156,0.07501918288142438,0.23230109942272947,0.19326975928773737,0.20457647800465048,0.19326975928773737,-0.14030038747657644,-0.19708429401052166 +4,9,0.1795435014714412,0.13605173844597301,0.24770362447157948,0.19326975928773737,0.22176429676645734,0.19326975928773737,-0.13299365743578936,-0.19708429401052166 +4,10,0.19240730058413158,0.16402499307972448,0.2616949490088366,0.19708429401052166,0.23751826947924037,0.19708429401052166,-0.12677792171627292,-0.2250575486442731 +4,11,0.20322924782632065,0.16402499307972448,0.2788026803681999,0.19708429401052166,0.25700498297667135,0.19708429401052166,-0.11857192925154157,-0.23904417596114885 +4,-1,0.20322924782632065,0.16402499307972448,0.2788026803681999,0.19708429401052166,0.25700498297667135,0.19708429401052166,-0.11857192925154157,-0.23904417596114885 +5,1,0.2167148354195988,0.17546859724807737,0.2970966789985337,0.227600571792796,0.2775287269055567,0.18691220141643022,-0.10956208551754683,-0.21615696762444314 +5,2,0.2342541272533144,0.17546859724807737,0.31224380943671876,0.227600571792796,0.29336920657043436,0.18691220141643022,-0.10294748084599689,-0.21615696762444314 +5,3,0.24056033070169486,0.20852789817887454,0.3172854234006855,0.227600571792796,0.29822121117964473,0.21488545605018167,-0.10256895603056826,-0.21615696762444314 +5,4,0.24661598040848576,0.20852789817887454,0.3193635293915088,0.25557382642654747,0.2993791296653484,0.21488545605018167,-0.10366863506017948,-0.21615696762444314 +5,5,0.2496006342565398,0.18309766669364594,0.31671696599967997,0.227600571792796,0.2948436237623708,0.18309766669364594,-0.10659989633587595,-0.21615696762444314 +5,6,0.24980644120787918,0.17928313197086163,0.31147296546967945,0.22378603707001168,0.28744968716481,0.18309766669364594,-0.11029938894754743,-0.20598487503035168 +5,7,0.24579407556753846,0.17419708567381592,0.30600059681931324,0.22378603707001168,0.280763186238965,0.18309766669364594,-0.11436916435251283,-0.22887208336705742 +5,8,0.24373185413587736,0.17928313197086163,0.2997540594645137,0.22378603707001168,0.2733080763264731,0.19326975928773737,-0.1170751217739402,-0.20089882873330597 +5,9,0.24309115646885737,0.17928313197086163,0.29544036750531044,0.22378603707001168,0.2681357924184571,0.20725638660461312,-0.11865666848499383,-0.17928313197086163 +5,10,0.2340720301501599,0.17928313197086163,0.2889322513473441,0.227600571792796,0.2609351449095855,0.22887208336705742,-0.12200041291195818,-0.17928313197086163 +5,11,0.22702587733219784,0.17928313197086163,0.28828629584536564,0.227600571792796,0.26000946983462797,0.20471336345609026,-0.12389901119754106,-0.17928313197086163 +5,-1,0.22702587733219784,0.17928313197086163,0.28828629584536564,0.227600571792796,0.26000946983462797,0.20471336345609026,-0.12389901119754106,-0.17928313197086163 +6,1,0.2202398881382316,0.17928313197086163,0.28783315722404107,0.227600571792796,0.25920254429698036,0.18691220141643022,-0.12535725236380374,-0.17928313197086163 +6,2,0.21432659125751358,0.11825057640631301,0.28806920377341566,0.22378603707001168,0.2591763003345211,0.18309766669364594,-0.12622693797777457,-0.15639592363415591 +6,3,0.20830985940754632,0.11316453010926729,0.2874716051225109,0.22378603707001168,0.25845123727093855,0.18309766669364594,-0.128050204572002,-0.15639592363415591 +6,4,0.20687365819613776,0.11316453010926729,0.2900670422142052,0.227600571792796,0.26202791833949113,0.18309766669364594,-0.12816964539290662,-0.15639592363415591 +6,5,0.21523480419789154,0.14113778474301875,0.2992126438162638,0.227600571792796,0.273539201451529,0.18309766669364594,-0.1255571197225206,-0.18436917826790739 +6,6,0.22547679438327733,0.17419708567381592,0.3068349992009625,0.227600571792796,0.28232972630741165,0.19326975928773737,-0.12237088921057328,-0.1983558055847831 +6,7,0.23526707310178324,0.17419708567381592,0.31201908743991535,0.22378603707001168,0.28814865287035735,0.19326975928773737,-0.11981200740766956,-0.1983558055847831 +6,8,0.24251844616240661,0.2021703403075674,0.3142929863900303,0.22378603707001168,0.2901791783160077,0.20725638660461312,-0.11783719281238111,-0.1983558055847831 +6,9,0.24106806304022374,0.2021703403075674,0.3103897437715215,0.23777266438688743,0.28474356526887024,0.2250575486442731,-0.11808984070453428,-0.18436917826790739 +6,10,0.23737000904331848,0.1907267361392145,0.30546575853505886,0.23777266438688743,0.2779826701472747,0.2250575486442731,-0.11894129323453126,-0.18436917826790739 +6,11,0.23379673714652754,0.1907267361392145,0.3007362946767967,0.23777266438688743,0.2717253417424303,0.21742847919870456,-0.12027556013832177,-0.15639592363415591 +6,-1,0.23379673714652754,0.1907267361392145,0.3007362946767967,0.23777266438688743,0.2717253417424303,0.21742847919870456,-0.12027556013832177,-0.15639592363415591 +7,1,0.22504562094088545,0.1296941805746659,0.2927233051884268,0.25557382642654747,0.261707956970844,0.21742847919870456,-0.1227501200302139,-0.15639592363415591 +7,2,0.21361247660164567,0.10172092594091442,0.282548796512769,0.21742847919870456,0.2493356108320789,0.21361394447592028,-0.1258340432396013,-0.12587964585188158 +7,3,0.2053173246919024,0.11825057640631301,0.2740719939049722,0.21361394447592028,0.23897288782390527,0.21361394447592028,-0.12797952377639307,-0.12587964585188158 +7,4,0.2031493816837769,0.11825057640631301,0.2719729617013787,0.21361394447592028,0.23621809096369364,0.21361394447592028,-0.12807620930148544,-0.12587964585188158 +7,5,0.2062812548598548,0.11825057640631301,0.2729461876737645,0.21361394447592028,0.23715315313235052,0.21361394447592028,-0.12688911846414136,-0.10426394908943727 +7,6,0.2106514532564003,0.11825057640631301,0.27509773384238434,0.21361394447592028,0.23979760686429222,0.21361394447592028,-0.1256265008750545,-0.10426394908943727 +7,7,0.21420190134353412,0.10680697223796014,0.27675508570872154,0.20725638660461312,0.24186251288305788,0.21361394447592028,-0.12455360215288487,-0.12587964585188158 +7,8,0.21645026196433806,0.10172092594091442,0.2761444006221833,0.20725638660461312,0.24125188708784914,0.21742847919870456,-0.12377177825448628,-0.10426394908943727 +7,9,0.22286079056372027,0.15130987733711018,0.27877264965306475,0.20725638660461312,0.24396431079954845,0.21361394447592028,-0.12179269208541561,-0.10426394908943727 +7,10,0.23122815713146896,0.18436917826790739,0.2835259992180892,0.20344185188182884,0.24937644684566754,0.21361394447592028,-0.11908345315473651,-0.10426394908943727 +7,11,0.24216318805702505,0.24540173383245603,0.2860408717915275,0.20344185188182884,0.2520832596188477,0.21361394447592028,-0.11740692582805182,-0.15639592363415591 +7,-1,0.24216318805702505,0.24540173383245603,0.2860408717915275,0.20344185188182884,0.2520832596188477,0.21361394447592028,-0.11740692582805182,-0.15639592363415591 +8,1,0.25294166558646647,0.22378603707001168,0.29011244179406315,0.22887208336705742,0.25682359945176886,0.23904417596114885,-0.11509096650856725,-0.18436917826790739 +8,2,0.2622935912563509,0.22378603707001168,0.29289268397505336,0.23904417596114885,0.2599580753132145,0.23904417596114885,-0.112430410048435,-0.18436917826790739 +8,3,0.27104532649976876,0.22378603707001168,0.29674964192285147,0.2670174305949003,0.2644797350861832,0.23904417596114885,-0.10968006373146001,-0.18436917826790739 +8,4,0.27895444179717416,0.22378603707001168,0.3011209419224611,0.2670174305949003,0.2697632502410179,0.23904417596114885,-0.10668206985283309,-0.18436917826790739 +8,5,0.283491134282999,0.24540173383245603,0.3044886979337975,0.2670174305949003,0.27400794922087224,0.23904417596114885,-0.10443841763435,-0.18436917826790739 +8,6,0.2861747002555699,0.24540173383245603,0.30675132886264217,0.2670174305949003,0.2770374549433133,0.23904417596114885,-0.10246617181096561,-0.18436917826790739 +8,7,0.2886264806646882,0.24540173383245603,0.30878661083417724,0.2670174305949003,0.27961443941124076,0.23904417596114885,-0.10061906658479479,-0.18436917826790739 +8,8,0.2914339862389273,0.24540173383245603,0.3103283980970281,0.2670174305949003,0.28176846244348364,0.23904417596114885,-0.09905729129105022,-0.18436917826790739 +8,9,0.2911890493099097,0.24540173383245603,0.31049180253997416,0.2670174305949003,0.28228673477993727,0.23904417596114885,-0.09833265094117871,-0.18436917826790739 +8,10,0.29200218576776604,0.24540173383245603,0.31078316979233733,0.2670174305949003,0.28270730529699895,0.23904417596114885,-0.0974441234703406,-0.18436917826790739 +8,11,0.293420331190866,0.24540173383245603,0.31096802014588076,0.2670174305949003,0.2829948098288711,0.24285871068393314,-0.09660089681014779,-0.18436917826790739 +8,-1,0.293420331190866,0.24540173383245603,0.31096802014588076,0.2670174305949003,0.2829948098288711,0.24285871068393314,-0.09660089681014779,-0.18436917826790739 +9,1,0.29463937483609337,0.24540173383245603,0.31168539565094466,0.2670174305949003,0.2839298080937795,0.2708319653176846,-0.09565350259718645,-0.18436917826790739 +9,2,0.29456085713046626,0.24540173383245603,0.3117763673783413,0.2670174305949003,0.284173381938314,0.2708319653176846,-0.09507122053882232,-0.18436917826790739 +9,3,0.2945316495533631,0.24540173383245603,0.31183208760406406,0.2670174305949003,0.28433283265901993,0.2708319653176846,-0.09474798693136255,-0.18436917826790739 +9,4,0.2936192489747766,0.24540173383245603,0.3107599221510276,0.2670174305949003,0.28301977563315467,0.2708319653176846,-0.09470454464413451,-0.18436917826790739 +9,5,0.29392046841328023,0.23777266438688743,0.3099499680549142,0.2708319653176846,0.28199791497778504,0.2708319653176846,-0.09436308095465824,-0.18436917826790739 +9,6,0.29421910892606756,0.23777266438688743,0.3094527514225266,0.2708319653176846,0.2813610595238485,0.2708319653176846,-0.09407980757539504,-0.18436917826790739 +9,7,0.294694690411905,0.23777266438688743,0.30940350371130576,0.2708319653176846,0.28127404241625253,0.2708319653176846,-0.09373056781591102,-0.18436917826790739 +9,8,0.29477064411391,0.23777266438688743,0.30922414739227044,0.2708319653176846,0.28101273684097156,0.2708319653176846,-0.09344269461192596,-0.18436917826790739 +9,9,0.29497815679311795,0.23777266438688743,0.3093610186024877,0.2708319653176846,0.2811635566862548,0.2708319653176846,-0.09316760178216572,-0.18436917826790739 +9,10,0.2947714373060331,0.23777266438688743,0.30930056621703345,0.2708319653176846,0.2810973598079407,0.2708319653176846,-0.09310644106453599,-0.18436917826790739 +9,11,0.2947452818294745,0.23777266438688743,0.3093278218890188,0.2708319653176846,0.28113436432455097,0.2708319653176846,-0.09305635600832704,-0.18436917826790739 +9,-1,0.2947452818294745,0.23777266438688743,0.3093278218890188,0.2708319653176846,0.28113436432455097,0.2708319653176846,-0.09305635600832704,-0.18436917826790739 diff --git a/modules.json b/modules.json new file mode 100644 index 0000000..f7640f9 --- /dev/null +++ b/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" + } +] \ No newline at end of file diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..810f993 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e61ea5ee7df5327600e887bb88c8f5a0c19a3d99d2a11b32a12af7e1271a34 +size 470696369 diff --git a/sentence_bert_config.json b/sentence_bert_config.json new file mode 100644 index 0000000..5fd1042 --- /dev/null +++ b/sentence_bert_config.json @@ -0,0 +1,4 @@ +{ + "max_seq_length": 128, + "do_lower_case": false +} \ No newline at end of file diff --git a/similarity_evaluation_sts-test_results.csv b/similarity_evaluation_sts-test_results.csv new file mode 100644 index 0000000..31929f3 --- /dev/null +++ b/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,-1,0.6898108228450448,0.1487076040083709,0.612508583192453,0.12327569489755234,0.5447838507576881,0.11706803401555063,0.6087343178007307,0.3575742671402244 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..2ea7ad0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "unk_token": "", "sep_token": "", "pad_token": "", "cls_token": "", "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..52031af --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3313815c3d2e1b78b5182b09e66e6cd4cdd54df67a35c4a318c23d461821a4 +size 17082913 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..65c0407 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"do_lower_case": true, "unk_token": "", "sep_token": "", "pad_token": "", "cls_token": "", "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "", "eos_token": "", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2/", "tokenizer_class": "BertTokenizer"} \ No newline at end of file diff --git a/unigram.json b/unigram.json new file mode 100644 index 0000000..81c58e0 --- /dev/null +++ b/unigram.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6 +size 14763234