Add new SentenceTransformer model.

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin 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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 512, "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:a48c18a6b1c5cc997b8e2c450cc635fd6ab5623a3b663bd6df90d89d1d58abb0
+size 1575975

README.md

@@ -0,0 +1,87 @@
+---
+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 512 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 11 with parameters:
+```
+{'batch_size': 15, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 1,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 2,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (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})
+  (2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_distiluse-base-multilingual-cased-v1/",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "vocab_size": 119547
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

eval/similarity_evaluation_results.csv

@@ -0,0 +1,13 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,1,0.3025718391868595,0.4246848658033177,0.30613216767618595,0.3839964954269519,0.291456965945577,0.33695056717927896,0.31795452080383496,0.37382440283286045
+0,2,0.27656141228062237,0.3471226597733704,0.2851882345135896,0.34839417134763184,0.27416005197025156,0.31533487041683467,0.28653443667613077,0.38908254172399764
+0,3,0.24403790678564918,0.2657459190206389,0.2634073556741324,0.3077058009712661,0.25611335116079237,0.30134824309995895,0.17619659316926284,0.13732325002023446
+0,4,0.21098129324041823,0.2949906852286518,0.2385149345721428,0.2657459190206389,0.23317545394998027,0.2962621968029132,0.08417653083533543,0.026701743059490034
+0,5,0.1976705490414005,0.2975337083771747,0.22733910849598027,0.25048778012950174,0.22354018727227948,0.27973254633751465,0.04767283605454447,-0.07374767130716295
+0,6,0.19370668242784028,0.22378603707001168,0.22412071908030348,0.31533487041683467,0.21695073779937513,0.32296393986240324,0.017518013325996513,-0.11697906483205156
+0,7,0.17814033055451065,0.10172092594091442,0.21167623303774183,0.27973254633751465,0.1986903757134589,0.31533487041683467,-0.01754840207768673,-0.19199824771347596
+0,8,0.1620008725967935,0.04450290509915005,0.19612190690179201,0.20725638660461312,0.1799757426196444,0.23650115281262601,-0.038219590036530374,-0.2225145254957503
+0,9,0.14917397249472883,-0.0025430231485228604,0.182809151874608,0.10172092594091442,0.1651492577965719,0.1309656921489273,-0.049803707096675164,-0.2225145254957503
+0,10,0.14117026361938556,0.01907267361392145,0.17352335426986445,0.08773429862403868,0.15490273714950764,0.09536336806960725,-0.05482557519381782,-0.21488545605018167
+0,11,0.14059717628890844,0.005086046297045721,0.17255564632746279,0.08773429862403868,0.15359020238436324,0.08137674075273153,-0.054366378934212284,-0.21488545605018167
+0,-1,0.14059717628890844,0.005086046297045721,0.17255564632746279,0.08773429862403868,0.15359020238436324,0.08137674075273153,-0.054366378934212284,-0.21488545605018167

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:ecd92f4c8476a369fae14fcc6f6e88cc4a5db04f66040000017b9c46b256dcfa
+size 538972985

sentence_bert_config.json

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

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.7196434688031887,0.319190772367219,0.6909147720915559,0.32486216935103734,0.6747856036858331,0.3276897426323679,0.7107332528260147,0.289176244490106

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "old_models/distiluse-base-multilingual-cased-v1/0_Transformer/special_tokens_map.json", "name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_distiluse-base-multilingual-cased-v1/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}