Hemg commited on
Commit
c9cfcba
1 Parent(s): 271dc01

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sentence-transformers
3
+ pipeline_tag: sentence-similarity
4
+ tags:
5
+ - sentence-transformers
6
+ - feature-extraction
7
+ - sentence-similarity
8
+
9
+ ---
10
+
11
+ # {MODEL_NAME}
12
+
13
+ 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.
14
+
15
+ <!--- Describe your model here -->
16
+
17
+ ## Usage (Sentence-Transformers)
18
+
19
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
20
+
21
+ ```
22
+ pip install -U sentence-transformers
23
+ ```
24
+
25
+ Then you can use the model like this:
26
+
27
+ ```python
28
+ from sentence_transformers import SentenceTransformer
29
+ sentences = ["This is an example sentence", "Each sentence is converted"]
30
+
31
+ model = SentenceTransformer('{MODEL_NAME}')
32
+ embeddings = model.encode(sentences)
33
+ print(embeddings)
34
+ ```
35
+
36
+
37
+
38
+ ## Evaluation Results
39
+
40
+ <!--- Describe how your model was evaluated -->
41
+
42
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
43
+
44
+
45
+ ## Training
46
+ The model was trained with the parameters:
47
+
48
+ **DataLoader**:
49
+
50
+ `torch.utils.data.dataloader.DataLoader` of length 598 with parameters:
51
+ ```
52
+ {'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
53
+ ```
54
+
55
+ **Loss**:
56
+
57
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
58
+ ```
59
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
60
+ ```
61
+
62
+ Parameters of the fit()-Method:
63
+ ```
64
+ {
65
+ "epochs": 2,
66
+ "evaluation_steps": 50,
67
+ "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
68
+ "max_grad_norm": 1,
69
+ "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
70
+ "optimizer_params": {
71
+ "lr": 2e-05
72
+ },
73
+ "scheduler": "WarmupLinear",
74
+ "steps_per_epoch": null,
75
+ "warmup_steps": 119,
76
+ "weight_decay": 0.01
77
+ }
78
+ ```
79
+
80
+
81
+ ## Full Model Architecture
82
+ ```
83
+ SentenceTransformer(
84
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
85
+ (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
86
+ (2): Normalize()
87
+ )
88
+ ```
89
+
90
+ ## Citing & Authors
91
+
92
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "thenlper/gte-small",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.44.0",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.7.0",
4
+ "transformers": "4.44.0",
5
+ "pytorch": "2.4.0+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
eval/Information-Retrieval_evaluation_results.csv ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 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
2
+ 0,50,0.023582538886101356,0.04616156547917712,0.05352065562803145,0.06372303060712493,0.023582538886101356,0.023582538886101356,0.01538718849305904,0.04616156547917712,0.010704131125606288,0.05352065562803145,0.0063723030607124925,0.06372303060712493,0.036766314375446335,0.04325369274457803,0.03853220818837741,0.023917042983776553,0.04616156547917712,0.05352065562803145,0.06372303060712493,0.023917042983776553,0.023917042983776553,0.015387188493059038,0.04616156547917712,0.010704131125606288,0.05352065562803145,0.006372303060712494,0.06372303060712493,0.03689965142549187,0.04334883332318176,0.03867614403116339
3
+ 0,100,0.024418799130289347,0.050342866700117075,0.057869208897809,0.07058036460946647,0.024418799130289347,0.024418799130289347,0.016780955566705693,0.050342866700117075,0.0115738417795618,0.057869208897809,0.007058036460946647,0.07058036460946647,0.0399726423434401,0.04734478769111249,0.0415923973394692,0.024251547081451746,0.050175614651279475,0.0577019568489714,0.07007860846295368,0.024251547081451746,0.024251547081451746,0.016725204883759826,0.050175614651279475,0.01154039136979428,0.0577019568489714,0.007007860846295368,0.07007860846295368,0.03976078974824581,0.04706961257597185,0.04138988580539302
4
+ 0,150,0.030607124937280482,0.05653119250710821,0.0672353236327145,0.07777220270948319,0.030607124937280482,0.030607124937280482,0.018843730835702736,0.05653119250710821,0.0134470647265429,0.0672353236327145,0.007777220270948319,0.07777220270948319,0.04639233348465657,0.05396898349140625,0.04813932271457901,0.030607124937280482,0.05602943636059542,0.0669008195350393,0.07743769861180799,0.030607124937280482,0.030607124937280482,0.01867647878686514,0.05602943636059542,0.013380163907007862,0.0669008195350393,0.0077437698611808005,0.07743769861180799,0.04619070184800236,0.053731669445488364,0.04794112797911816
5
+ 0,200,0.03261414952333166,0.05903997323967219,0.07124937280481686,0.08295701622344874,0.03261414952333166,0.03261414952333166,0.019679991079890727,0.05903997323967219,0.014249874560963372,0.07124937280481686,0.008295701622344874,0.08295701622344874,0.04936537139246621,0.05747385526539776,0.05133089929589361,0.03261414952333166,0.05853821709315939,0.07091486870714166,0.08329152032112393,0.03261414952333166,0.03261414952333166,0.01951273903105313,0.05853821709315939,0.014182973741428335,0.07091486870714166,0.008329152032112394,0.08329152032112393,0.049282409066653904,0.05747646351997944,0.05126102389588475
6
+ 0,250,0.03161063723030607,0.060043485532697775,0.07058036460946647,0.08462953671182472,0.03161063723030607,0.03161063723030607,0.020014495177565924,0.060043485532697775,0.014116072921893295,0.07058036460946647,0.008462953671182473,0.08462953671182472,0.04904858804758449,0.057606269017111876,0.05100872309493791,0.03177788927914367,0.06071249372804817,0.07091486870714166,0.08479678876066232,0.03177788927914367,0.03177788927914367,0.020237497909349388,0.06071249372804817,0.014182973741428335,0.07091486870714166,0.008479678876066233,0.08479678876066232,0.04933616865378024,0.05787337165694404,0.051322794708820514
7
+ 0,300,0.03194514132798127,0.05937447733734738,0.07007860846295368,0.08529854490717512,0.03194514132798127,0.03194514132798127,0.019791492445782457,0.05937447733734738,0.014015721692590737,0.07007860846295368,0.008529854490717512,0.08529854490717512,0.04912132941485678,0.05779829125326069,0.05132189388964644,0.03177788927914367,0.05920722528850978,0.06957685231644088,0.08496404080949992,0.03177788927914367,0.03177788927914367,0.019735741762836594,0.05920722528850978,0.013915370463288178,0.06957685231644088,0.008496404080949992,0.08496404080949992,0.04889972045014696,0.05754706789006916,0.051144012769738546
8
+ 0,350,0.03646094664659642,0.06338852650944975,0.07275464124435524,0.08897808998160227,0.03646094664659642,0.03646094664659642,0.021129508836483242,0.06338852650944975,0.014550928248871048,0.07275464124435524,0.008897808998160228,0.08897808998160227,0.05310411838259309,0.0616836706597109,0.05538826411247286,0.03629369459775882,0.06305402241177455,0.07242013714668005,0.08864358588392708,0.03629369459775882,0.03629369459775882,0.021018007470591512,0.06305402241177455,0.014484027429336011,0.07242013714668005,0.008864358588392707,0.08864358588392708,0.052833727570305626,0.061392335007394376,0.05511900096141513
9
+ 0,400,0.03462117410938284,0.061214249874560964,0.07141662485365445,0.0868038133467135,0.03462117410938284,0.03462117410938284,0.020404749958186984,0.061214249874560964,0.014283324970730893,0.07141662485365445,0.00868038133467135,0.0868038133467135,0.05113074331589131,0.059662183764620375,0.05358420802428783,0.03445392206054524,0.06087974577688577,0.07091486870714166,0.0859675531025255,0.03445392206054524,0.03445392206054524,0.020293248592295254,0.06087974577688577,0.014182973741428335,0.07091486870714166,0.008596755310252552,0.0859675531025255,0.05082318538163995,0.05923584162657828,0.05331071275181635
10
+ 0,450,0.033952165914032446,0.061214249874560964,0.07158387690249206,0.08529854490717512,0.033952165914032446,0.033952165914032446,0.020404749958186988,0.061214249874560964,0.014316775380498411,0.07158387690249206,0.008529854490717512,0.08529854490717512,0.05055040525436913,0.05889335179333282,0.052928882080342736,0.03411941796287005,0.061214249874560964,0.07141662485365445,0.08529854490717512,0.03411941796287005,0.03411941796287005,0.020404749958186988,0.061214249874560964,0.014283324970730893,0.07141662485365445,0.008529854490717512,0.08529854490717512,0.050609009841322945,0.058930332972676344,0.052933396802333395
11
+ 0,500,0.03712995484194681,0.0682388359257401,0.08094999163739756,0.09449740759324302,0.03712995484194681,0.03712995484194681,0.022746278641913364,0.0682388359257401,0.016189998327479513,0.08094999163739756,0.009449740759324303,0.09449740759324302,0.05586749390060976,0.06517225756168178,0.05812157269756394,0.03712995484194681,0.0682388359257401,0.08061548753972236,0.09416290349556782,0.03712995484194681,0.03712995484194681,0.022746278641913364,0.0682388359257401,0.016123097507944474,0.08061548753972236,0.009416290349556784,0.09416290349556782,0.05583756109345668,0.0650733907166999,0.05813060014690576
12
+ 0,550,0.03411941796287005,0.06573005519317611,0.07777220270948319,0.09098511456765346,0.03411941796287005,0.03411941796287005,0.021910018397725373,0.06573005519317611,0.015554440541896638,0.07777220270948319,0.009098511456765346,0.09098511456765346,0.053068278657842145,0.06223233772265387,0.055318650344823375,0.03428667001170764,0.06573005519317611,0.07777220270948319,0.09098511456765346,0.03428667001170764,0.03428667001170764,0.021910018397725373,0.06573005519317611,0.015554440541896638,0.07777220270948319,0.009098511456765344,0.09098511456765346,0.05315588687389993,0.06229789117644267,0.05539125601882426
13
+ 0,-1,0.031443385181468476,0.05954172938618498,0.07124937280481686,0.0868038133467135,0.031443385181468476,0.031443385181468476,0.019847243128728324,0.05954172938618498,0.014249874560963372,0.07124937280481686,0.00868038133467135,0.0868038133467135,0.04917316427602425,0.05818817775519503,0.05155587075590613,0.03194514132798127,0.05954172938618498,0.07091486870714166,0.0863020572002007,0.03194514132798127,0.03194514132798127,0.019847243128728324,0.05954172938618498,0.014182973741428335,0.07091486870714166,0.00863020572002007,0.0863020572002007,0.04933205372241998,0.05818828087405434,0.05173859077854106
14
+ 1,50,0.029436360595417294,0.05469141996989463,0.06506104699782572,0.08111724368623516,0.029436360595417294,0.029436360595417294,0.01823047332329821,0.05469141996989463,0.013012209399565147,0.06506104699782572,0.008111724368623516,0.08111724368623516,0.045580430979327076,0.05406190802644771,0.04809593373284472,0.029436360595417294,0.05519317611640743,0.06573005519317611,0.08178625188158554,0.029436360595417294,0.029436360595417294,0.01839772537213581,0.05519317611640743,0.013146011038635224,0.06573005519317611,0.008178625188158557,0.08178625188158554,0.04584524672331993,0.05442861417550546,0.0483367210381028
15
+ 1,100,0.033784913865194846,0.06205051011874895,0.07375815353738083,0.08947984612811508,0.033784913865194846,0.033784913865194846,0.02068350337291632,0.06205051011874895,0.014751630707476168,0.07375815353738083,0.008947984612811507,0.08947984612811508,0.05174864671854131,0.06079754406550658,0.05417926154910819,0.033952165914032446,0.06205051011874895,0.07375815353738083,0.08947984612811508,0.033952165914032446,0.033952165914032446,0.02068350337291632,0.06205051011874895,0.014751630707476168,0.07375815353738083,0.008947984612811507,0.08947984612811508,0.051832272742960116,0.06085927182038675,0.054262390172289475
16
+ 1,150,0.035122930255895635,0.06623181133968892,0.07911021910018398,0.08998160227462787,0.035122930255895635,0.035122930255895635,0.02207727044656297,0.06623181133968892,0.015822043820036796,0.07911021910018398,0.008998160227462786,0.08998160227462787,0.053693681854745524,0.062488358076782546,0.05607750440941799,0.035290182304733235,0.06639906338852651,0.07877571500250878,0.09014885432346546,0.035290182304733235,0.035290182304733235,0.022133021129508833,0.06639906338852651,0.015755143000501758,0.07877571500250878,0.009014885432346548,0.09014885432346546,0.053773325687525325,0.06258138156196613,0.05611696701541647
17
+ 1,200,0.03562468640240843,0.06539555109550092,0.07793945475832079,0.09165412276300385,0.03562468640240843,0.03562468640240843,0.021798517031833636,0.06539555109550092,0.015587890951664159,0.07793945475832079,0.009165412276300385,0.09165412276300385,0.053980466022613485,0.0630572905497149,0.05637027945908422,0.03562468640240843,0.06556280314433852,0.07827395885599599,0.09215587890951664,0.03562468640240843,0.03562468640240843,0.021854267714779503,0.06556280314433852,0.0156547917711992,0.07827395885599599,0.009215587890951666,0.09215587890951664,0.054104710401749995,0.06327259887909407,0.05648640770371627
18
+ 1,250,0.03729720689078441,0.06940960026760327,0.08128449573507275,0.09499916373975581,0.03729720689078441,0.03729720689078441,0.02313653342253442,0.06940960026760327,0.016256899147014555,0.08128449573507275,0.009499916373975584,0.09499916373975581,0.0565076975764381,0.06580881154287595,0.058989545633567626,0.03729720689078441,0.06924234821876568,0.08128449573507275,0.09483191169091822,0.03729720689078441,0.03729720689078441,0.02308078273958856,0.06924234821876568,0.016256899147014555,0.08128449573507275,0.009483191169091822,0.09483191169091822,0.05648008771440777,0.06574680653134034,0.05896005310387503
19
+ 1,300,0.03830071918381,0.06874059207225289,0.08195350393042315,0.0960026760327814,0.03830071918381,0.03830071918381,0.02291353069075096,0.06874059207225289,0.01639070078608463,0.08195350393042315,0.009600267603278142,0.0960026760327814,0.05720086440106507,0.06654550948179173,0.05978168131719851,0.038133467134972406,0.06924234821876568,0.08245526007693595,0.096169928081619,0.038133467134972406,0.038133467134972406,0.023080782739588555,0.06924234821876568,0.01649105201538719,0.08245526007693595,0.0096169928081619,0.096169928081619,0.057288472617122846,0.06666711992654326,0.05988298143098353
20
+ 1,350,0.037966215086134805,0.07007860846295368,0.08245526007693595,0.09750794447231978,0.037966215086134805,0.037966215086134805,0.02335953615431789,0.07007860846295368,0.01649105201538719,0.08245526007693595,0.009750794447231979,0.09750794447231978,0.05767952383607175,0.06727465472665319,0.06025455342157139,0.038133467134972406,0.06991135641411607,0.08228800802809834,0.09734069242348219,0.038133467134972406,0.038133467134972406,0.023303785471372022,0.06991135641411607,0.01645760160561967,0.08228800802809834,0.00973406924234822,0.09734069242348219,0.05773527451901761,0.06727465472665319,0.06032240634782736
21
+ 1,400,0.0384679712326476,0.0682388359257401,0.08228800802809834,0.09483191169091822,0.0384679712326476,0.0384679712326476,0.022746278641913364,0.0682388359257401,0.016457601605619668,0.08228800802809834,0.009483191169091822,0.09483191169091822,0.056933924821531395,0.06606947597810373,0.059642340830351206,0.0386352232814852,0.06890784412109048,0.08312426827228633,0.09566817193510621,0.0386352232814852,0.0386352232814852,0.022969281373696825,0.06890784412109048,0.016624853654457268,0.08312426827228633,0.00956681719351062,0.09566817193510621,0.05729444590458132,0.0665468772988933,0.05996109242617319
22
+ 1,450,0.037966215086134805,0.06857334002341528,0.08078273958855996,0.09483191169091822,0.037966215086134805,0.037966215086134805,0.022857780007805095,0.06857334002341528,0.01615654791771199,0.08078273958855996,0.009483191169091822,0.09483191169091822,0.05668895366587286,0.06588616657613866,0.05941180265022006,0.037966215086134805,0.06840608797457769,0.08061548753972236,0.09483191169091822,0.037966215086134805,0.037966215086134805,0.022802029324859228,0.06840608797457769,0.016123097507944474,0.08061548753972236,0.009483191169091822,0.09483191169091822,0.05664992818781075,0.0658508872361684,0.05936799151876658
23
+ 1,500,0.03896972737916039,0.06991135641411607,0.08178625188158554,0.0963371801304566,0.03896972737916039,0.03896972737916039,0.023303785471372022,0.06991135641411607,0.01635725037631711,0.08178625188158554,0.00963371801304566,0.0963371801304566,0.057728836642534524,0.0670149475338139,0.06046076337429554,0.039136979427997994,0.07007860846295368,0.08195350393042315,0.09650443217929419,0.039136979427997994,0.039136979427997994,0.02335953615431789,0.07007860846295368,0.01639070078608463,0.08195350393042315,0.009650443217929421,0.09650443217929419,0.05789310204764288,0.06717921104668435,0.060617639933744444
24
+ 1,550,0.0384679712326476,0.06991135641411607,0.08245526007693595,0.09650443217929419,0.0384679712326476,0.0384679712326476,0.023303785471372022,0.06991135641411607,0.016491052015387187,0.08245526007693595,0.009650443217929421,0.09650443217929419,0.057480414254122154,0.06687306451297426,0.060141894082521304,0.0384679712326476,0.06991135641411607,0.08245526007693595,0.0963371801304566,0.0384679712326476,0.0384679712326476,0.023303785471372022,0.06991135641411607,0.016491052015387187,0.08245526007693595,0.00963371801304566,0.0963371801304566,0.0574636890492384,0.06682471782852571,0.06013282339720233
25
+ 1,-1,0.03763171098845961,0.07007860846295368,0.08212075597926075,0.096169928081619,0.03763171098845961,0.03763171098845961,0.02335953615431789,0.07007860846295368,0.01642415119585215,0.08212075597926075,0.0096169928081619,0.096169928081619,0.05704894379003757,0.06647790066674919,0.05972895587447432,0.037798963037297205,0.07058036460946647,0.08295701622344874,0.09700618832580699,0.037798963037297205,0.037798963037297205,0.023526788203155485,0.07058036460946647,0.01659140324468975,0.08295701622344874,0.0097006188325807,0.09700618832580699,0.05747822404872074,0.0670114940743558,0.06009276045368868
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15a7b86ad2f2a59af1f69891df73f94468d80c3c2c08a086bb67092496af8f6
3
+ size 133462128
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff