Upload . with huggingface_hub

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 384, "out_features": 1536, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579e2cb38413bf2e5d742dc4e7e5ac8738a02bbf23d1fe5693ea55cb18e8584e
+size 2366655

README.md

@@ -0,0 +1,88 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1536 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 5629 with parameters:
+```
+{'batch_size': 256, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MSELoss.MSELoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 5000,
+    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 1e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 0,
+    "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})
+  (2): Dense({'in_features': 384, 'out_features': 1536, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "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": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.26.1",
+    "pytorch": "1.13.1+cu116"
+  }
+}

eval/mse_evaluation_TED2020-en-ja-dev.tsv.gz_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,MSE
+0,5000,15.336495637893677
+0,5000,12.954607605934143
+0,-1,12.912595272064209
+1,5000,12.687340378761292
+1,-1,12.669636309146881
+2,5000,12.557819485664368
+2,-1,12.54439651966095
+3,5000,12.48689889907837
+3,-1,12.482773512601852
+4,5000,12.444017827510834
+4,-1,12.438619136810303
+5,5000,12.410631030797958
+5,-1,12.410634011030197
+6,5000,12.390589714050293
+6,-1,12.387491017580032
+7,5000,12.376674264669418
+7,-1,12.375471740961075
+8,5000,12.36639991402626
+8,-1,12.365838885307312
+9,5000,12.362902611494064
+9,-1,12.362852692604065

eval/mse_evaluation_TED2020-en-ko-dev.tsv.gz_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,MSE
+0,5000,15.262071788311005
+0,5000,12.939640879631042
+0,-1,12.899290025234222
+1,5000,12.65731006860733
+1,-1,12.63882964849472
+2,5000,12.517587840557098
+2,-1,12.504678964614868
+3,5000,12.440747022628784
+3,-1,12.435487657785416
+4,5000,12.395995855331421
+4,-1,12.389052659273148
+5,5000,12.358856946229935
+5,-1,12.358789891004562
+6,5000,12.337474524974823
+6,-1,12.334243953227997
+7,5000,12.321463972330093
+7,-1,12.321139872074127
+8,5000,12.31139600276947
+8,-1,12.310890853404999
+9,5000,12.307607382535934
+9,-1,12.307436019182205

eval/similarity_evaluation_STS.en-en.txt_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,5000,0.7655745634242543,0.7836504132433898,0.7846846467902374,0.7838618313464806,0.7836273750089683,0.7822623572974621,0.5494118147277136,0.541470976153046
+0,5000,0.5433990711978052,0.6367006089229957,0.6259777625370179,0.642350085034129,0.6278392957870316,0.6448336711506177,0.17866541866368144,0.17027075867749752
+0,-1,0.5514187157185174,0.6441905757206711,0.6343457732981078,0.651206197174321,0.6356036005712372,0.6526211608788242,0.17619759098086993,0.1669272774762566
+1,5000,0.6259974781249414,0.7028448766559378,0.699061169438624,0.7103110108674464,0.7003582184299956,0.7107961193149017,0.3107339912723675,0.28766815615132896
+1,-1,0.6320028753018896,0.7069686828558587,0.7018952028092444,0.7151782399971442,0.7032080521125087,0.7145897288774501,0.325787489252297,0.30655278991248835
+2,5000,0.6532984908864011,0.7200200989544714,0.7167047871038497,0.7264994872193732,0.7180204407529439,0.7284187791988854,0.3939642284126825,0.37640994393225324
+2,-1,0.6595646756177629,0.7207808197290466,0.7207058362824752,0.7303038598853518,0.7219193242676952,0.7325018393643925,0.3926348211295626,0.37538091436502835
+3,5000,0.6691316041398592,0.7268093108395388,0.7271152475614135,0.7360536634963155,0.727627390318982,0.7374436414249986,0.42470505212920584,0.40564253284832236
+3,-1,0.6740698957264698,0.7324541741920593,0.7309594678451006,0.7400790641791616,0.7312940067366801,0.7411177036601633,0.4340591834670731,0.41405236059271755
+4,5000,0.6807875710274601,0.7361097853927722,0.7350881349038876,0.7451135058085766,0.7345268271030532,0.7434967339147597,0.4468829533734607,0.42710300789822797
+4,-1,0.6801609860450414,0.7378207344416022,0.7356695044433241,0.7460164533070492,0.734915697335349,0.7453107012392775,0.4471632459627408,0.4222465418719602
+5,5000,0.687594182855673,0.746239018910121,0.7412780017392339,0.7525212117443221,0.740047690811974,0.752489691227134,0.4545440684939544,0.42849029505105385
+5,-1,0.6870067772718528,0.7474283418391438,0.7411894808586456,0.7520572451071759,0.739837237251545,0.751876578728171,0.4601486601510168,0.4344857280581537
+6,5000,0.6897349652251179,0.7495851908872195,0.7434885283062591,0.7556036876873837,0.7420581753647143,0.7548368165679913,0.460962258383408,0.4365022723650874
+6,-1,0.6897381062614594,0.7491638922672424,0.7430627618238766,0.7541691197587759,0.7414341614238988,0.7540784021727224,0.4631013001864373,0.4377907696042872
+7,5000,0.6949463226109924,0.7541103070864615,0.7473258964764949,0.7592827470777122,0.7457521688697132,0.7582387260449954,0.47035650643256577,0.44594920200428007
+7,-1,0.6945277705869185,0.7537605062249844,0.7467006246144783,0.758808786130238,0.7451742148625806,0.7576640532011399,0.4746718702140449,0.45128116656422634
+8,5000,0.6970970176332015,0.7548437357059107,0.7485574923693642,0.7597217279390386,0.746960239958548,0.7599858083696264,0.48098707129883783,0.4573730831056457
+8,-1,0.6976548965751576,0.7553219250154466,0.7488958919812253,0.7609679415576204,0.7472972687653574,0.7599277644904142,0.48139796322076295,0.4568818243133732
+9,5000,0.6975963820651174,0.7558831439800144,0.7490601641362845,0.7604932118170439,0.7474640856660989,0.7607053987132367,0.48040339603301346,0.45827410862136303
+9,-1,0.6977032578721013,0.755818565359434,0.7491281424746049,0.7603794304379261,0.7475372403588282,0.7603940375068668,0.4806896585543663,0.4585566400864023

eval/translation_evaluation_TED2020-en-ja-dev.tsv.gz_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,src2trg,trg2src
+0,5000,0.914,0.896
+0,5000,0.649,0.613
+0,-1,0.687,0.67
+1,5000,0.821,0.793
+1,-1,0.826,0.797
+2,5000,0.842,0.825
+2,-1,0.846,0.823
+3,5000,0.858,0.837
+3,-1,0.858,0.839
+4,5000,0.868,0.851
+4,-1,0.869,0.855
+5,5000,0.869,0.858
+5,-1,0.872,0.856
+6,5000,0.873,0.852
+6,-1,0.873,0.854
+7,5000,0.877,0.854
+7,-1,0.877,0.855
+8,5000,0.879,0.856
+8,-1,0.879,0.852
+9,5000,0.88,0.854
+9,-1,0.879,0.854

eval/translation_evaluation_TED2020-en-ko-dev.tsv.gz_results.csv

@@ -0,0 +1,22 @@
+epoch,steps,src2trg,trg2src
+0,5000,0.949,0.93
+0,5000,0.719,0.713
+0,-1,0.751,0.736
+1,5000,0.872,0.84
+1,-1,0.877,0.847
+2,5000,0.899,0.885
+2,-1,0.904,0.887
+3,5000,0.911,0.898
+3,-1,0.913,0.9
+4,5000,0.922,0.901
+4,-1,0.918,0.907
+5,5000,0.921,0.911
+5,-1,0.92,0.908
+6,5000,0.923,0.911
+6,-1,0.926,0.912
+7,5000,0.93,0.914
+7,-1,0.929,0.914
+8,5000,0.927,0.916
+8,-1,0.929,0.915
+9,5000,0.929,0.915
+9,-1,0.929,0.915

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accc8fd2a364dded93a81ad811808e91a32f8fd9a3cd889f89488bdda2603405
+size 470686253

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
+size 17082913

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
+size 14763234