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": 768, "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 sha256:3ddb54cb980b5bd7b34e3c8b8de7a00e460030c91d88da6b5209ceef4deaaa40
+size 1183935

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 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)
+```
+
+
+
+## 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 2815 with parameters:
+```
+{'batch_size': 512, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`__main__.TwosentCosineSimilarity` 
+
+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": 10000,
+    "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': 768, '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": "/root/.cache/torch/sentence_transformers/krenerd_msmarco-distilbert-cos-v5_en-ko-ja_v1.2/",
+  "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 +1,11 @@
+epoch,steps,MSE
+0,-1,0.07739276625216007
+1,-1,0.07871822454035282
+2,-1,0.08125526364892721
+3,-1,0.08475463255308568
+4,-1,0.08700703037902713
+5,-1,0.08860978414304554
+6,-1,0.08973792428150773
+7,-1,0.0897291989531368
+8,-1,0.08952902862802148
+9,-1,0.08921260596252978

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

@@ -0,0 +1,11 @@
+epoch,steps,MSE
+0,-1,0.07465468370355666
+1,-1,0.07578869699500501
+2,-1,0.07826064247637987
+3,-1,0.0814322498627007
+4,-1,0.08360195206478238
+5,-1,0.0850712473038584
+6,-1,0.08588494383729994
+7,-1,0.08597023552283645
+8,-1,0.0857240695040673
+9,-1,0.08541608694940805

eval/similarity_evaluation_STS.en-en.txt_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,-1,0.8147488209561811,0.8331157146252346,0.8277546087969095,0.8268392877392996,0.8273958288660017,0.8275185164450473,0.7606816647799216,0.7747712373101335
+1,-1,0.8153415968996263,0.8344895478987728,0.8276120202495106,0.8277633770480815,0.8271664910945171,0.8275173632553942,0.7633356839873534,0.775377046274626
+2,-1,0.8185088239925613,0.8374832282385364,0.8296574252288444,0.8283399718746922,0.8293530105636183,0.8286947698913335,0.7701822995605637,0.7859717840153252
+3,-1,0.8185649097106077,0.8388897352189159,0.830535693306541,0.8297587795447062,0.8297611311825416,0.8284287674779903,0.7661368511416309,0.7829062215205107
+4,-1,0.8220624500218002,0.8402858634924164,0.8312255446967585,0.8293297929937077,0.8303915890103634,0.8281485423922574,0.7729072256712058,0.7896839015090461
+5,-1,0.8212640029246959,0.839186873752896,0.8313674563372009,0.8295577401484944,0.8305136705950673,0.8289223326495693,0.7710450461750568,0.7868631996172657
+6,-1,0.8236747604269405,0.841999887713655,0.8309973484381926,0.8311971914388246,0.8302432913004139,0.8300140188546191,0.7748782868135271,0.793443299778549
+7,-1,0.8224808215190609,0.8408105647846322,0.8308845203125629,0.8303126949748035,0.8299220603983455,0.8290757068734478,0.7715620357773744,0.7902301290081222
+8,-1,0.8237444463407186,0.8416485492659733,0.8312203379386249,0.830231202905976,0.8303916892139727,0.8291806471318909,0.7737773647243381,0.7915424588334885
+9,-1,0.8240155968968835,0.8420690790928483,0.8314834651691148,0.8312233304042976,0.8305852158002336,0.8303261488540912,0.7731504635060087,0.7915639850403486

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

@@ -0,0 +1,11 @@
+epoch,steps,src2trg,trg2src
+0,-1,0.905,0.887
+1,-1,0.903,0.888
+2,-1,0.909,0.887
+3,-1,0.904,0.89
+4,-1,0.907,0.889
+5,-1,0.904,0.89
+6,-1,0.907,0.89
+7,-1,0.907,0.89
+8,-1,0.908,0.889
+9,-1,0.908,0.889

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

@@ -0,0 +1,11 @@
+epoch,steps,src2trg,trg2src
+0,-1,0.948,0.919
+1,-1,0.947,0.92
+2,-1,0.948,0.918
+3,-1,0.945,0.923
+4,-1,0.948,0.919
+5,-1,0.946,0.919
+6,-1,0.948,0.921
+7,-1,0.947,0.921
+8,-1,0.946,0.923
+9,-1,0.948,0.923

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 sha256:7d61999326bbf82f03d0278d87d573c01573cb1821fb42c7c95632c9b4b90027
+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": "/root/.cache/torch/sentence_transformers/krenerd_msmarco-distilbert-cos-v5_en-ko-ja_v1.2/",
+  "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