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
+}

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 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 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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (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): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-distilroberta-v1/",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

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

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
+0,1,0.45892171995983294,0.5136906760016178,0.4480500006536557,0.5136906760016178,0.4538208185638512,0.49970404868474205,0.45892148035278574,0.5136906760016178
+0,2,0.4336270843877642,0.42341335422905624,0.41576341834421354,0.42341335422905624,0.4217401446469101,0.4132412616349648,0.4336271335257007,0.42341335422905624
+0,3,0.3499986701736571,0.2492162685552403,0.31773573574512187,0.2492162685552403,0.314040772546085,0.22124301392148887,0.34999811942626746,0.2492162685552403
+0,4,0.31265979468790317,0.1894552245649531,0.27286963351619414,0.1894552245649531,0.26246153933199057,0.1296941805746659,0.31266011544144784,0.1894552245649531
+0,5,0.3218422038296091,0.22124301392148887,0.27823331363036974,0.22124301392148887,0.2608168527527259,0.15512441205989447,0.3218424832364223,0.22124301392148887
+0,6,0.332789473538533,0.26447440744637746,0.28680091084906456,0.26447440744637746,0.26401944945779493,0.18436917826790739,0.3327895330513663,0.26447440744637746
+0,7,0.3258309349135759,0.21234243290165886,0.27796750597138814,0.21234243290165886,0.2532409434146122,0.12715115742614302,0.32583037653512426,0.21234243290165886
+0,8,0.3273312491066775,0.24413022225819456,0.27775084625932117,0.24413022225819456,0.251878680346386,0.15893894678267878,0.3273309257438753,0.24413022225819456
+0,9,0.3259744891270688,0.24413022225819456,0.2757345748899191,0.24413022225819456,0.24908663427154365,0.18055464354512307,0.3259746906431779,0.24413022225819456
+0,10,0.33823291410351386,0.2581168495750703,0.2881122635596565,0.2581168495750703,0.2622311119772618,0.2199715023472274,0.33823268102542015,0.2581168495750703
+0,11,0.3461446144842104,0.2581168495750703,0.29619977212433857,0.2581168495750703,0.27099007670581826,0.2199715023472274,0.3461443467964613,0.2581168495750703
+0,-1,0.3461446144842104,0.2581168495750703,0.29619977212433857,0.2581168495750703,0.27099007670581826,0.2199715023472274,0.3461443467964613,0.2581168495750703

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"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ea82f1842ed02592f3007bf50a46cc3d5b1cc43b6583ccef948d92544524d3
+size 328517361

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "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,-1,0.763199158207649,0.387052531119154,0.7482557311349456,0.387052531119154,0.7450649094260047,0.4043754800725933,0.7631991923155116,0.38697783338492403

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-distilroberta-v1/", "tokenizer_class": "RobertaTokenizer"}