Upload . with huggingface_hub

.gitattributes

@@ -32,3 +32,4 @@ 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

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
+}

README.md

@@ -0,0 +1,126 @@
+---
+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, mean 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 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: XLMRobertaModel 
+  (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 -->

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/v1_3/",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

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
+0,5000,0.07691268692724407
+0,-1,0.07659784168936312
+1,5000,0.07561671664007008
+1,-1,0.07537561468780041
+2,5000,0.07464137743227184
+2,-1,0.07426953525282443
+3,5000,0.07380967726930976
+3,-1,0.07369623053818941
+4,5000,0.07318426505662501
+4,-1,0.0730453000869602
+5,5000,0.07272141519933939
+5,-1,0.0727076199837029
+6,5000,0.07254749652929604
+6,-1,0.07255459786392748
+7,5000,0.07214996148832142
+7,-1,0.07210787734948099
+8,5000,0.07201439584605396
+8,-1,0.07204361027106643
+9,5000,0.07192625780589879
+9,-1,0.07193719502538443

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

@@ -0,0 +1,21 @@
+epoch,steps,MSE
+0,5000,0.07377860601991415
+0,-1,0.07347434875555336
+1,5000,0.07236491073854268
+1,-1,0.07207684684544802
+2,5000,0.07120443042367697
+2,-1,0.07081329822540283
+3,5000,0.07022445788607001
+3,-1,0.07012199494056404
+4,5000,0.06962649640627205
+4,-1,0.06940726307220757
+5,5000,0.06906852941028774
+5,-1,0.0691152410581708
+6,5000,0.06885575712658465
+6,-1,0.06884735194034874
+7,5000,0.06839782581664622
+7,-1,0.06838650442659855
+8,5000,0.06827132892794907
+8,-1,0.06832123035565019
+9,5000,0.06816776585765183
+9,-1,0.06817689863964915

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
+0,5000,0.8058496824544271,0.8297968348032624,0.8174334725164674,0.8201065821472401,0.815605531816456,0.8178497899958851,0.7620924493486533,0.7789626973030435
+0,-1,0.8061044416438005,0.8303615133367901,0.8173695980001617,0.8202257450780729,0.815428989612524,0.8171928562900997,0.7631613950433525,0.7808231766102411
+1,5000,0.8124699355985517,0.8343227197956067,0.8236325421272224,0.8242995797263544,0.8215744837211111,0.821983206109583,0.7730917857434711,0.7913406506441746
+1,-1,0.8118196986182875,0.832748615918959,0.8229541520590496,0.8222361390401897,0.8207273866828355,0.8195346000792421,0.7706977435211454,0.7865745178074093
+2,5000,0.8160323057157925,0.8381736044442651,0.8260837321712862,0.8268085360152136,0.824039710401451,0.8225524974017234,0.7798620802971341,0.7997389464920376
+2,-1,0.8173524236602239,0.8387794134087577,0.8290101557755543,0.83091273799103,0.8270505459691999,0.826835443773789,0.7813529276351607,0.7997085791645027
+3,5000,0.8176675837249465,0.8394140521145808,0.8303532709696446,0.831759947989597,0.8287062879087163,0.828978454546026,0.7788263288267748,0.7982713204600373
+3,-1,0.8194653710801287,0.8389204869430018,0.8309676243351617,0.830860844456635,0.8293633589927677,0.828426461098684,0.7858544729921929,0.8042878952774464
+4,5000,0.8218346968201119,0.8404626859059103,0.8319360774269859,0.8318241422136261,0.8307420339996787,0.8297199554930476,0.788175637434133,0.8080791984606882
+4,-1,0.8218538206611165,0.84190148219658,0.8318905329210022,0.8312794523007546,0.8305112661429764,0.8297276434240691,0.7901646681887011,0.810287172250057
+5,5000,0.823378429886499,0.8429512691775629,0.8337320427914859,0.8346452285019578,0.8324433114262023,0.832468006436675,0.7901926522931996,0.8092354632863186
+5,-1,0.8233312120784968,0.8427679120227006,0.8342533607497408,0.8342493000543516,0.8328566188308405,0.8320482454029025,0.7897656184284972,0.8097816907853946
+6,5000,0.8242118589427546,0.8440429553826128,0.8332388673570393,0.8340186621237072,0.8321195142661825,0.8313486436799478,0.7961944386166991,0.814578575346246
+6,-1,0.8250336035074726,0.8432199623667636,0.8342397037969053,0.8345991009158288,0.8331722586642143,0.8326548231604969,0.7945989487682296,0.8109575598351298
+7,5000,0.8274247908545429,0.8472495914116714,0.8371442302482218,0.8385099514264549,0.8359426360568065,0.8358691471205771,0.7993260596115057,0.8173519964622443
+7,-1,0.8257564600874887,0.8447344847779948,0.836336285857069,0.8375405033246465,0.8352112022250694,0.8359817753100418,0.7959236427135716,0.8142602950019568
+8,5000,0.8274728971938476,0.8460445082240547,0.8370489556956594,0.8374962977212731,0.835926020820942,0.8361232332408369,0.7989449274404368,0.8176056981859531
+8,-1,0.8271991970778428,0.8472580481357951,0.8369609124431712,0.8382108909097192,0.8358389014911632,0.8357803515172789,0.7973294738349457,0.816267998188216
+9,5000,0.827126400027193,0.8461898101203607,0.837066923558911,0.8379183651343521,0.8359670108444548,0.8361551381545761,0.7973825938798208,0.8158167166372551
+9,-1,0.8269876448748019,0.8458861368450122,0.8369880252085725,0.837783057548374,0.8358798774570008,0.8358664563447196,0.7972899158614187,0.8156702615512961

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

@@ -0,0 +1,21 @@
+epoch,steps,src2trg,trg2src
+0,5000,0.906,0.883
+0,-1,0.902,0.889
+1,5000,0.904,0.886
+1,-1,0.908,0.887
+2,5000,0.909,0.891
+2,-1,0.908,0.888
+3,5000,0.904,0.889
+3,-1,0.908,0.888
+4,5000,0.911,0.886
+4,-1,0.91,0.887
+5,5000,0.911,0.885
+5,-1,0.909,0.889
+6,5000,0.91,0.885
+6,-1,0.911,0.885
+7,5000,0.91,0.885
+7,-1,0.912,0.885
+8,5000,0.911,0.883
+8,-1,0.912,0.885
+9,5000,0.912,0.882
+9,-1,0.912,0.883

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

@@ -0,0 +1,21 @@
+epoch,steps,src2trg,trg2src
+0,5000,0.955,0.932
+0,-1,0.953,0.934
+1,5000,0.953,0.932
+1,-1,0.954,0.934
+2,5000,0.954,0.933
+2,-1,0.952,0.933
+3,5000,0.953,0.935
+3,-1,0.953,0.936
+4,5000,0.954,0.936
+4,-1,0.952,0.936
+5,5000,0.952,0.934
+5,-1,0.952,0.932
+6,5000,0.954,0.936
+6,-1,0.954,0.938
+7,5000,0.953,0.936
+7,-1,0.954,0.935
+8,5000,0.952,0.934
+8,-1,0.954,0.937
+9,5000,0.953,0.936
+9,-1,0.953,0.936

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:c8bea356a28ccaa7ec5afbd4a875e1be37d8f6c3e6868dd1b621e04693fad451
+size 1112245805

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "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": "/content/drive/MyDrive/v1_3/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}