Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "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,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,91 @@
+---
+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 384 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 30 with parameters:
+```
+{'batch_size': 10, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 50,
+    "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 30,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, '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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-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": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.6.1",
+    "pytorch": "1.8.1"
+  }
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cos_sim-Accuracy@1,cos_sim-Accuracy@3,cos_sim-Accuracy@5,cos_sim-Accuracy@10,cos_sim-Precision@1,cos_sim-Recall@1,cos_sim-Precision@3,cos_sim-Recall@3,cos_sim-Precision@5,cos_sim-Recall@5,cos_sim-Precision@10,cos_sim-Recall@10,cos_sim-MRR@10,cos_sim-NDCG@10,cos_sim-MAP@100,dot_score-Accuracy@1,dot_score-Accuracy@3,dot_score-Accuracy@5,dot_score-Accuracy@10,dot_score-Precision@1,dot_score-Recall@1,dot_score-Precision@3,dot_score-Recall@3,dot_score-Precision@5,dot_score-Recall@5,dot_score-Precision@10,dot_score-Recall@10,dot_score-MRR@10,dot_score-NDCG@10,dot_score-MAP@100
+0,-1,0.92,0.95,0.96,0.98,0.92,0.92,0.31666666666666665,0.95,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9389285714285716,0.9488207658565767,0.939354292049414,0.92,0.95,0.96,0.98,0.92,0.92,0.31666666666666665,0.95,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9389285714285716,0.9488207658565767,0.939354292049414
+1,-1,0.92,0.95,0.97,0.98,0.92,0.92,0.31666666666666665,0.95,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9397619047619048,0.9495654595662303,0.9402171105730429,0.92,0.95,0.97,0.98,0.92,0.92,0.31666666666666665,0.95,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9397619047619048,0.9495654595662303,0.9402171105730429
+2,-1,0.93,0.96,0.96,0.98,0.93,0.93,0.31999999999999995,0.96,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9447619047619048,0.953204702740128,0.9452284362020671,0.93,0.96,0.96,0.98,0.93,0.93,0.31999999999999995,0.96,0.19199999999999995,0.96,0.09799999999999998,0.98,0.9447619047619048,0.953204702740128,0.9452284362020671
+3,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420000000000001,0.9513584925505694,0.9425035577449371,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420000000000001,0.9513584925505694,0.9425035577449371
+4,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427432155657962,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427432155657962
+5,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425967261904762,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425967261904762
+6,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909
+7,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9422619047619049,0.951567991521211,0.9427683013503909
+8,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196
+9,-1,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196,0.92,0.96,0.97,0.98,0.92,0.92,0.31999999999999995,0.96,0.19399999999999995,0.97,0.09799999999999998,0.98,0.9420833333333333,0.9513893069557349,0.9425897299218196

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5361cb8adf099468f69c22aee86d75b41a54ad28a7e02e42421e87e8c6797705
+size 90864192

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_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}