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 sha256:647329e1f5c51af68d3318eb4f11725d465f1cccc1e098d34def14e2fced7a75
+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 +1,21 @@
+epoch,steps,MSE
+0,5000,14.090806245803833
+0,-1,14.041325449943542
+1,5000,13.756965100765228
+1,-1,13.731969892978668
+2,5000,13.59749436378479
+2,-1,13.583962619304657
+3,5000,13.513915240764618
+3,-1,13.504542410373688
+4,5000,13.454103469848633
+4,-1,13.447530567646027
+5,5000,13.414488732814789
+5,-1,13.411219418048859
+6,5000,13.38731050491333
+6,-1,13.383430242538452
+7,5000,13.36725503206253
+7,-1,13.365139067173004
+8,5000,13.354888558387756
+8,-1,13.354355096817017
+9,5000,13.350608944892883
+9,-1,13.350439071655273

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

@@ -0,0 +1,21 @@
+epoch,steps,MSE
+0,5000,14.07613605260849
+0,-1,14.028197526931763
+1,5000,13.723884522914886
+1,-1,13.6981800198555
+2,5000,13.554643094539642
+2,-1,13.540615141391754
+3,5000,13.463293015956879
+3,-1,13.45561146736145
+4,5000,13.401681184768677
+4,-1,13.395018875598907
+5,5000,13.358426094055176
+5,-1,13.355842232704163
+6,5000,13.329306244850159
+6,-1,13.32559585571289
+7,5000,13.307400047779083
+7,-1,13.305117189884186
+8,5000,13.294477760791779
+8,-1,13.29374760389328
+9,5000,13.289938867092133
+9,-1,13.289736211299896

eval/similarity_evaluation_STS.en-en.txt_results.csv

@@ -0,0 +1,21 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,5000,0.5584715887070306,0.6106435199153483,0.6204285313762743,0.6239282647204628,0.6227081729309086,0.6273839897146172,0.027078836467990197,0.024595997717015587
+0,-1,0.5640430594026749,0.6186581880052393,0.6297266900683036,0.635489759787113,0.6316028120937888,0.6394859463320773,0.045096663803948285,0.040924010016982315
+1,5000,0.649871173945208,0.6909243552105845,0.7049685502601991,0.706320590270748,0.7046418130084839,0.7055979247547292,0.24960006006965837,0.2243157605688369
+1,-1,0.654431513986989,0.6967910153730746,0.7092238454103693,0.7106462046599828,0.7089872621386482,0.7106415919013699,0.261963468297667,0.2357957635666594
+2,5000,0.6909860756397656,0.726778559115453,0.7370819527467755,0.7370196520291642,0.7360345226996672,0.736457279874943,0.34336794441295065,0.32259058281639424
+2,-1,0.6925700008812241,0.7266924542880124,0.7376618810301628,0.7381028815100905,0.7366987361383045,0.7364538203059834,0.3534225145052863,0.3319829281453343
+3,5000,0.7140525697384895,0.7446187874473444,0.7544234287953692,0.7552584995845194,0.7531777594196064,0.7534291563979586,0.39927080695014033,0.38474942710780186
+3,-1,0.7172877346684642,0.7465599900302677,0.7574907890397503,0.7588060953543806,0.7564181276915455,0.7577989763905669,0.3966220132454458,0.3820006073710722
+4,5000,0.7277845825777627,0.7558562362214394,0.7667535083086637,0.7674703936155867,0.7659218899158776,0.7662829926693193,0.4277044285837922,0.41529626783199275
+4,-1,0.7270212141806779,0.7567734063923016,0.7668600640782219,0.7683260603382771,0.7659780476000536,0.7673643001674902,0.4211974950752341,0.40880150370504786
+5,5000,0.7372409756414472,0.7675249779258391,0.7756372225059973,0.7778275742877221,0.7749333533921645,0.7776945730810506,0.43997674548946264,0.42831846979272375
+5,-1,0.7385167697807389,0.7691117668886722,0.7770976301025854,0.7794554936815202,0.7764028043370276,0.7785748411830099,0.4485518914525139,0.43741867374284765
+6,5000,0.7471523207701108,0.7759455687736643,0.7839808264785212,0.7884303843559941,0.7832520194143462,0.7883934822870909,0.45761539360357023,0.4494825751017514
+6,-1,0.7462694309237172,0.7755292673088513,0.783523102715065,0.7870769240996628,0.7828458536185017,0.7866898367727313,0.45699358423571385,0.4476870588116851
+7,5000,0.7494204953256803,0.7786755530793913,0.7873064897829533,0.7914044604716529,0.7866547871962861,0.7911150098686943,0.4669221147456885,0.45799888069079403
+7,-1,0.7496235816376139,0.7792994286817841,0.7874282131988112,0.790786735214077,0.7867875683309122,0.790889369093214,0.4682683340095791,0.4605701092209275
+8,5000,0.753771049087656,0.7833767228990252,0.7907834229307895,0.794613018483467,0.7900408518349241,0.7952957067581742,0.4777997267685433,0.470604781186712
+8,-1,0.7540753944433641,0.7833525059163076,0.7910391569628871,0.7943181863287933,0.7903067170762724,0.7952368940858598,0.4795988561212103,0.4734016504923259
+9,5000,0.7542413301647596,0.7830299972099566,0.7915892895561383,0.7945799603800745,0.7908470471363674,0.7958972873606049,0.47685777735667634,0.47095650403094463
+9,-1,0.7543749648330546,0.7832541003992327,0.7916491895457073,0.7947237246901762,0.7909162343463914,0.7962232556359156,0.4775897823612356,0.4715715385126629

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

@@ -0,0 +1,21 @@
+epoch,steps,src2trg,trg2src
+0,5000,0.797,0.772
+0,-1,0.81,0.792
+1,5000,0.887,0.861
+1,-1,0.893,0.868
+2,5000,0.902,0.888
+2,-1,0.901,0.888
+3,5000,0.911,0.898
+3,-1,0.911,0.897
+4,5000,0.913,0.899
+4,-1,0.913,0.9
+5,5000,0.913,0.901
+5,-1,0.914,0.902
+6,5000,0.918,0.899
+6,-1,0.916,0.903
+7,5000,0.919,0.903
+7,-1,0.919,0.905
+8,5000,0.922,0.907
+8,-1,0.921,0.906
+9,5000,0.921,0.907
+9,-1,0.921,0.907

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

@@ -0,0 +1,21 @@
+epoch,steps,src2trg,trg2src
+0,5000,0.837,0.818
+0,-1,0.855,0.842
+1,5000,0.919,0.905
+1,-1,0.922,0.908
+2,5000,0.936,0.918
+2,-1,0.939,0.921
+3,5000,0.941,0.927
+3,-1,0.941,0.926
+4,5000,0.946,0.929
+4,-1,0.946,0.927
+5,5000,0.947,0.93
+5,-1,0.947,0.933
+6,5000,0.948,0.934
+6,-1,0.948,0.936
+7,5000,0.949,0.936
+7,-1,0.95,0.936
+8,5000,0.949,0.938
+8,-1,0.949,0.938
+9,5000,0.95,0.938
+9,-1,0.95,0.939

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:e06f80685fbda0f9a023647c6f740c78d72d48954c3bf6b27cdc082d29448386
+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