Add model files

.gitattributes

@@ -15,3 +15,4 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth 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
+}

Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
+0,0,0.2716,0.3712,0.4146,0.4728,0.2716,0.2328662213380489,0.14366666666666666,0.33802247127615276,0.10107999999999999,0.3816533603616589,0.060779999999999994,0.44206509817925427,0.3328388888888883,0.35044908626720733,0.3227257729819207,0.2372,0.3446,0.3914,0.4532,0.2372,0.20217122954822955,0.13219999999999998,0.310081212534894,0.09496000000000002,0.3585161058763781,0.05806,0.4234658398242798,0.30277023809523773,0.32353167381698217,0.2938001455419752

README.md

@@ -0,0 +1,140 @@
+---
+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, max 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 3227 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': 'cos_sim'}
+  ```
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 4333 with parameters:
+```
+{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.OnlineContrastiveLoss.OnlineContrastiveLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "callback": null,
+    "epochs": 10,
+    "evaluation_steps": 0,
+    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 1000,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, '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})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

binary_classification_evaluation_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhatten_accuracy,manhatten_accuracy_threshold,manhatten_f1,manhatten_precision,manhatten_recall,manhatten_f1_threshold,manhatten_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
+0,0,0.7702253117308161,0.8136365413665771,0.6979915362396721,0.6179601546238478,0.8018365614630758,0.7241197824478149,0.7273756292687126,0.7708744691785453,151.6903076171875,0.6960194634047442,0.6191163210099189,0.7947372482444633,173.9261474609375,0.7233593435586896,0.77119904790241,6.848635673522949,0.6965292399646812,0.6220052162309698,0.7913419245312139,7.865234375,0.7238513749310248,0.7503448648941062,89.73575592041016,0.6813400734716946,0.5743779777660137,0.8372559611081102,76.39668273925781,0.6675158822135764

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/ricardo-filho_sbertimbau-base-nli-sts/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": "4.9.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.9.2",
+    "pytorch": "1.9.0+cu102"
+  }
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
+0,-1,0.2372,0.3242,0.3554,0.4078,0.2372,0.2039062290662554,0.12533333333333332,0.2938633469103995,0.08712,0.3280917875983665,0.05274000000000001,0.3826247651734231,0.2900503968253966,0.3052020756906472,0.2814680806372763,0.2246,0.3116,0.3532,0.4024,0.2246,0.19034069197462072,0.12046666666666665,0.27990193389929136,0.08688000000000001,0.3239384489056603,0.05242,0.3773540333754943,0.279230714285714,0.29493277813134056,0.2696738583687664
+1,-1,0.2208,0.3118,0.3538,0.4082,0.2208,0.1906023514263514,0.11926666666666665,0.28253839382839385,0.08567999999999999,0.325132235986236,0.05235999999999999,0.38053508537661174,0.27735992063492054,0.2953773273030226,0.2701761026645177,0.2106,0.3016,0.3408,0.4036,0.2106,0.1788491011211011,0.11553333333333332,0.2709065547230547,0.083,0.31205115440115444,0.05212000000000001,0.37663087651230526,0.26722928571428584,0.2860272569696295,0.25960388318959554
+2,-1,0.198,0.283,0.3204,0.3694,0.198,0.16886889067365382,0.10773333333333332,0.25501663781540096,0.07708000000000002,0.2922982309999942,0.047439999999999996,0.3452344194781826,0.25025515873015874,0.26600558669808155,0.24265405641353405,0.1912,0.2758,0.3146,0.3684,0.1912,0.16261696825396826,0.10586666666666665,0.24906748379398377,0.0762,0.28756046047512607,0.04746,0.3440479792165473,0.24343380952380964,0.2608228663061413,0.23712489466787215
+3,-1,0.1998,0.2804,0.3152,0.3672,0.1998,0.17151564763014762,0.10633333333333332,0.2520259297456929,0.07544,0.2880516318389213,0.04706,0.34275876673034567,0.24949087301587275,0.2648501857855016,0.24227772929859312,0.1906,0.268,0.3092,0.359,0.1906,0.16278115190365192,0.10326666666666665,0.24162145538671856,0.0756,0.283845314860578,0.0464,0.3354570622973518,0.24015365079365084,0.2568533515694136,0.23530341548681064
+4,-1,0.1968,0.2762,0.3102,0.3592,0.1968,0.17016064213564214,0.10466666666666666,0.24930712377388692,0.07512,0.28618810037038983,0.045880000000000004,0.33510609893608034,0.24559555555555562,0.26094188680292607,0.2399871622700095,0.1898,0.2716,0.3126,0.3654,0.1898,0.1627792746142746,0.104,0.24519903086679407,0.07616,0.2872368989255645,0.04714,0.3408886166230717,0.24154563492063513,0.2594723458233706,0.23630997636367293
+5,-1,0.1894,0.2706,0.306,0.3544,0.1894,0.1631732197334829,0.10266666666666666,0.24311746078775023,0.07356,0.27857326605558186,0.04514,0.32743737344811796,0.23978984126984138,0.2540043870624939,0.23257951338359809,0.1866,0.2672,0.308,0.3622,0.1866,0.15845578144078146,0.10213333333333333,0.23911385338637964,0.07476000000000001,0.28067046972325915,0.04658,0.3357389825903664,0.23869309523809537,0.2548313201127815,0.23161900852925163
+6,-1,0.1816,0.2654,0.2994,0.348,0.1816,0.15586289072039072,0.10206666666666667,0.2398298539968803,0.07264000000000001,0.27497268346273607,0.04456,0.32337269232229765,0.23300769841269853,0.24863415991088741,0.22718751644942842,0.1784,0.2634,0.301,0.3574,0.1784,0.15224938644688643,0.10159999999999998,0.23655610258162887,0.07352,0.273933197550987,0.04582000000000001,0.33046281723539617,0.2311533333333336,0.24860618814199464,0.22535783343335383
+7,-1,0.1786,0.256,0.2974,0.3464,0.1786,0.15335733516483516,0.0976,0.2292645877543509,0.07136,0.26993428218857163,0.04432,0.32070174447475214,0.2287288888888892,0.2444608510132748,0.22260881605887525,0.1738,0.2596,0.3014,0.3552,0.1738,0.14775749389499387,0.09906666666666665,0.2311811556309188,0.07292,0.27298328849805165,0.045540000000000004,0.32864914362245945,0.22775571428571456,0.24507739118715577,0.22104170154478342
+8,-1,0.179,0.2598,0.2982,0.3472,0.179,0.15465218364968364,0.09879999999999999,0.2338106414784046,0.07176,0.27176947526450157,0.044360000000000004,0.3226426356392146,0.23036642857142875,0.2465777955077192,0.22481408188887958,0.1784,0.2588,0.3008,0.3574,0.1784,0.15201192612942613,0.09913333333333332,0.23295999518025837,0.07228,0.27373936681739314,0.0457,0.33156838254143517,0.23093293650793661,0.24860076192908165,0.22515725621653632
+9,-1,0.1752,0.2544,0.2958,0.3428,0.1752,0.15139218364968365,0.0964,0.22872714330990648,0.07108,0.26983756799633113,0.04356,0.31727919224050805,0.22551055555555582,0.24144376187203143,0.2198879713485739,0.1724,0.2526,0.2946,0.351,0.1724,0.14731359279609277,0.0962,0.22645712998989315,0.07112,0.26801078239304554,0.044520000000000004,0.3243359777240304,0.22449666666666707,0.24204975091667325,0.21904290798551887

eval/binary_classification_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhatten_accuracy,manhatten_accuracy_threshold,manhatten_f1,manhatten_precision,manhatten_recall,manhatten_f1_threshold,manhatten_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,-1,0.8281085174866788,0.7948580980300903,0.7634191970067635,0.7151041315629845,0.8187360135812949,0.7476930618286133,0.8151048640819258,0.8245381515241675,165.2333221435547,0.7572025352924229,0.7099061381592275,0.8112508681225403,177.52490234375,0.8084572351667939,0.824592247978145,7.556525230407715,0.7571945668924489,0.7069057815845824,0.8151863569719886,8.086832046508789,0.8088021749278818,0.7946228124746423,96.57695007324219,0.7302025163156832,0.6472833542076698,0.8374874604521954,88.6935806274414,0.7558786818494108
+1,-1,0.831760028130156,0.7951562404632568,0.7673825737733544,0.7008803266139322,0.8478277644880006,0.7270604372024536,0.821759469380718,0.829244543020205,162.31619262695312,0.7644511799090713,0.7179261267366994,0.8174241839648121,183.00323486328125,0.8173954562760868,0.8296773146520245,7.416135787963867,0.7648623441224222,0.6923702313946216,0.854309746122386,8.718894004821777,0.8174915253851984,0.8019528819885856,104.71066284179688,0.737308324665302,0.652279743528853,0.8478277644880006,93.76701354980469,0.7658575852386661
+2,-1,0.8301100862838441,0.7982156276702881,0.76747077841333,0.7111535422702133,0.8334748051547187,0.7435590028762817,0.8210934524467175,0.8276757458548593,173.00244140625,0.7616950620848976,0.7155645981688709,0.8141831931476194,191.7120819091797,0.8158416556592514,0.8268913472721863,7.834885597229004,0.761994355597366,0.7173513182096873,0.8125626977390231,8.67160415649414,0.8159628525600515,0.8031700522030781,118.7221908569336,0.7412330806245023,0.672149673530889,0.826143992592021,108.9227294921875,0.7729112538541285
+3,-1,0.8306510508236186,0.76955646276474,0.7681235738107777,0.7046245008373052,0.8442009414306659,0.7077353000640869,0.8247504631017505,0.8291633983392389,186.51699829101562,0.7636949516648764,0.7123772627079019,0.8229801682228567,211.0557098388672,0.8199215716178877,0.8291093018852614,8.396418571472168,0.7637145677619518,0.7030834144758196,0.8357897985955707,9.732316970825195,0.8201137002721581,0.8103107841281004,126.5792236328125,0.7453589003902935,0.6652732339755241,0.8473647657998302,111.54228210449219,0.7801433275141978
+4,-1,0.8284601444375321,0.8132146596908569,0.7642968639137222,0.7073346903933285,0.8312369781618952,0.7584837675094604,0.8203747004522858,0.8263774309594006,178.55079650878906,0.7596507684537123,0.713327461210109,0.8124083648429663,192.71424865722656,0.8153904723812119,0.8264585756403667,7.830205917358398,0.759636946075814,0.7050079281183932,0.823443166911027,8.865616798400879,0.8155123836651277,0.8046847529144464,132.4188232421875,0.7409640641785354,0.6724745250974965,0.824986495871595,120.85781860351562,0.7732877093057904
+5,-1,0.827892131670769,0.7898639440536499,0.7640205716684743,0.6988607270865336,0.8425804460220696,0.7287073135375977,0.8208624811798182,0.8249438749289985,185.56210327148438,0.7571314509690062,0.7146968139773895,0.8049232193842117,203.48995971679688,0.8146468772429272,0.8255118876957616,8.402811050415039,0.7575704410681077,0.6946589446589446,0.8330118064665484,9.567122459411621,0.8149429541260684,0.8101755429931567,134.74575805664062,0.7463411250606922,0.6777952755905512,0.8303109807855544,121.89347839355469,0.7865134799706808
+6,-1,0.8279732763517351,0.8023936152458191,0.76194795227796,0.6952950913605399,0.8427347789181264,0.7389289140701294,0.8196527319299838,0.8248627302480322,182.92852783203125,0.7556316138721055,0.6901875717749139,0.8347866347712015,209.47003173828125,0.8141934621741183,0.8252414054258743,8.026567459106445,0.7562751891395035,0.6978534612122398,0.825372328111737,9.37405776977539,0.8144742104561814,0.8085256011468448,136.46832275390625,0.7440861704706819,0.6750031418876461,0.8289219847210433,126.04867553710938,0.7826206417005237
+7,-1,0.8281355657136674,0.8015906810760498,0.7629180435019427,0.7205075445816187,0.8106335365383132,0.760754406452179,0.820322749870146,0.8248356820210435,186.18832397460938,0.7579685507862303,0.7004647509327747,0.825758160351879,208.84426879882812,0.8146155789865794,0.8251061642909308,8.251300811767578,0.7581335616438357,0.7049691501360048,0.8199706767497492,9.397960662841797,0.8147861459043289,0.8100403018582132,137.55056762695312,0.7450723638869745,0.6731212253284353,0.8342464696350027,127.28717041015625,0.7835050277802293
+8,-1,0.8278109869898028,0.8023335337638855,0.7644187951978911,0.7099655902593965,0.8279188208966741,0.7439565658569336,0.8199270555952481,0.8238078493954721,184.7388458251953,0.7580362770502137,0.693890634015001,0.8352496334593719,212.94998168945312,0.8137452039727104,0.8238078493954721,8.191852569580078,0.7576195291058789,0.7120070589832349,0.8094760398178872,9.342428207397461,0.8138742580920406,0.8119607259744124,135.5657501220703,0.7472978139227748,0.6798406475275073,0.8296164827532989,126.12296295166016,0.7876263874229076
+9,-1,0.8275134564929268,0.8055418729782104,0.7647100324537887,0.7043342647345506,0.8364071301797978,0.7457376718521118,0.8202416399695003,0.8246192962051337,182.28091430664062,0.7587397800958555,0.6982551728611274,0.8306968130256964,209.54336547851562,0.8144546159621295,0.8247545373400773,8.307082176208496,0.7583735452739143,0.7019376026272578,0.8246778300794815,9.426965713500977,0.814567996283235,0.8103919288090665,136.38003540039062,0.7470442576640044,0.6815578465063001,0.8264526583841346,129.10833740234375,0.785838858270554

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 sha256:5f5febceaed8dc1fb01aa41a6521528de5f77590d332735de75bbefef879289c
+size 435773873

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 75,
+  "do_lower_case": false
+}

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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "/root/.cache/torch/sentence_transformers/ricardo-filho_sbertimbau-base-nli-sts/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}