Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,10 @@
+{
+  "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,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,92 @@
+---
+library_name: sentence-transformers
+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 161 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": 3,
+    "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": 48,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, '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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "danielheinz/e5-base-sts-en-de",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "4.41.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.36.0",
+    "pytorch": "2.0.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,13 @@
+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
+0,50,0.18421052631578946,0.3526315789473684,0.43157894736842106,0.5684210526315789,0.18421052631578946,0.18421052631578946,0.11754385964912283,0.3526315789473684,0.0863157894736842,0.43157894736842106,0.05684210526315789,0.5684210526315789,0.2964421470342523,0.3606548184276387,0.3179161459044444,0.18421052631578946,0.3526315789473684,0.43157894736842106,0.5684210526315789,0.18421052631578946,0.18421052631578946,0.11754385964912283,0.3526315789473684,0.0863157894736842,0.43157894736842106,0.05684210526315789,0.5684210526315789,0.2964421470342523,0.3606548184276387,0.3179161459044444
+0,100,0.16842105263157894,0.3263157894736842,0.3973684210526316,0.5131578947368421,0.16842105263157894,0.16842105263157894,0.10877192982456141,0.3263157894736842,0.07947368421052632,0.3973684210526316,0.051315789473684204,0.5131578947368421,0.26967314118629915,0.3273578208738344,0.292784748827701,0.16842105263157894,0.3263157894736842,0.3973684210526316,0.5131578947368421,0.16842105263157894,0.16842105263157894,0.10877192982456141,0.3263157894736842,0.07947368421052632,0.3973684210526316,0.051315789473684204,0.5131578947368421,0.26967314118629915,0.3273578208738344,0.292784748827701
+0,150,0.15,0.29473684210526313,0.3631578947368421,0.48947368421052634,0.15,0.15,0.0982456140350877,0.29473684210526313,0.07263157894736842,0.3631578947368421,0.048947368421052635,0.48947368421052634,0.24091165413533844,0.2992786248715443,0.26425222312986635,0.15,0.29473684210526313,0.3631578947368421,0.48947368421052634,0.15,0.15,0.0982456140350877,0.29473684210526313,0.07263157894736842,0.3631578947368421,0.048947368421052635,0.48947368421052634,0.24091165413533844,0.2992786248715443,0.26425222312986635
+0,-1,0.13157894736842105,0.27631578947368424,0.33421052631578946,0.46842105263157896,0.13157894736842105,0.13157894736842105,0.09210526315789473,0.27631578947368424,0.0668421052631579,0.33421052631578946,0.046842105263157886,0.46842105263157896,0.22438387635756066,0.28163081778692756,0.2493602760220718,0.13157894736842105,0.27631578947368424,0.33421052631578946,0.46842105263157896,0.13157894736842105,0.13157894736842105,0.09210526315789473,0.27631578947368424,0.0668421052631579,0.33421052631578946,0.046842105263157886,0.46842105263157896,0.22438387635756066,0.28163081778692756,0.2493602760220718
+1,50,0.1763157894736842,0.29736842105263156,0.36578947368421055,0.531578947368421,0.1763157894736842,0.1763157894736842,0.09912280701754388,0.29736842105263156,0.07315789473684212,0.36578947368421055,0.05315789473684209,0.531578947368421,0.2650689223057644,0.326895225145251,0.2863376275723089,0.1763157894736842,0.29736842105263156,0.36578947368421055,0.531578947368421,0.1763157894736842,0.1763157894736842,0.09912280701754388,0.29736842105263156,0.07315789473684212,0.36578947368421055,0.05315789473684209,0.531578947368421,0.2650689223057644,0.326895225145251,0.2863376275723089
+1,100,0.1368421052631579,0.27631578947368424,0.32894736842105265,0.48157894736842105,0.1368421052631579,0.1368421052631579,0.09210526315789473,0.27631578947368424,0.06578947368421052,0.32894736842105265,0.0481578947368421,0.48157894736842105,0.23116750208855483,0.28970816558613627,0.2556165491380115,0.1368421052631579,0.27631578947368424,0.32894736842105265,0.48157894736842105,0.1368421052631579,0.1368421052631579,0.09210526315789473,0.27631578947368424,0.06578947368421052,0.32894736842105265,0.0481578947368421,0.48157894736842105,0.23116750208855483,0.28970816558613627,0.2556165491380115
+1,150,0.08157894736842106,0.2578947368421053,0.3263157894736842,0.4473684210526316,0.08157894736842106,0.08157894736842106,0.08596491228070174,0.2578947368421053,0.06526315789473683,0.3263157894736842,0.04473684210526316,0.4473684210526316,0.18769841269841275,0.24915441558526105,0.21316398985343735,0.08157894736842106,0.2578947368421053,0.3263157894736842,0.4473684210526316,0.08157894736842106,0.08157894736842106,0.08596491228070174,0.2578947368421053,0.06526315789473683,0.3263157894736842,0.04473684210526316,0.4473684210526316,0.18769841269841275,0.24915441558526105,0.21316398985343735
+1,-1,0.11052631578947368,0.26052631578947366,0.33157894736842103,0.46842105263157896,0.11052631578947368,0.11052631578947368,0.0868421052631579,0.26052631578947366,0.0663157894736842,0.33157894736842103,0.04684210526315789,0.46842105263157896,0.209139515455305,0.27004200521858807,0.23339221671005944,0.11052631578947368,0.26052631578947366,0.33157894736842103,0.46842105263157896,0.11052631578947368,0.11052631578947368,0.0868421052631579,0.26052631578947366,0.0663157894736842,0.33157894736842103,0.04684210526315789,0.46842105263157896,0.209139515455305,0.27004200521858807,0.23339221671005944
+2,50,0.12368421052631579,0.26842105263157895,0.33421052631578946,0.46578947368421053,0.12368421052631579,0.12368421052631579,0.08947368421052632,0.26842105263157895,0.0668421052631579,0.33421052631578946,0.04657894736842106,0.46578947368421053,0.21791771094402682,0.2761851490006137,0.24295744086571633,0.12368421052631579,0.26842105263157895,0.33421052631578946,0.46578947368421053,0.12368421052631579,0.12368421052631579,0.08947368421052632,0.26842105263157895,0.0668421052631579,0.33421052631578946,0.04657894736842106,0.46578947368421053,0.21791771094402682,0.2761851490006137,0.24295744086571633
+2,100,0.11052631578947368,0.2710526315789474,0.3394736842105263,0.4763157894736842,0.11052631578947368,0.11052631578947368,0.09035087719298245,0.2710526315789474,0.06789473684210527,0.3394736842105263,0.04763157894736843,0.4763157894736842,0.2122535505430243,0.2742722298608094,0.23639319833575217,0.11052631578947368,0.2710526315789474,0.3394736842105263,0.4763157894736842,0.11052631578947368,0.11052631578947368,0.09035087719298245,0.2710526315789474,0.06789473684210527,0.3394736842105263,0.04763157894736843,0.4763157894736842,0.2122535505430243,0.2742722298608094,0.23639319833575217
+2,150,0.10263157894736842,0.2736842105263158,0.3394736842105263,0.4789473684210526,0.10263157894736842,0.10263157894736842,0.09122807017543859,0.2736842105263158,0.06789473684210527,0.3394736842105263,0.04789473684210526,0.4789473684210526,0.2084607351712616,0.27208677144273347,0.23253632470322755,0.10263157894736842,0.2736842105263158,0.3394736842105263,0.4789473684210526,0.10263157894736842,0.10263157894736842,0.09122807017543859,0.2736842105263158,0.06789473684210527,0.3394736842105263,0.04789473684210526,0.4789473684210526,0.2084607351712616,0.27208677144273347,0.23253632470322755
+2,-1,0.10263157894736842,0.2736842105263158,0.3394736842105263,0.4789473684210526,0.10263157894736842,0.10263157894736842,0.09122807017543859,0.2736842105263158,0.06789473684210527,0.3394736842105263,0.04789473684210526,0.4789473684210526,0.2084607351712616,0.27208677144273347,0.23255385974443543,0.10263157894736842,0.2736842105263158,0.3394736842105263,0.4789473684210526,0.10263157894736842,0.10263157894736842,0.09122807017543859,0.2736842105263158,0.06789473684210527,0.3394736842105263,0.04789473684210526,0.4789473684210526,0.2084607351712616,0.27208677144273347,0.23255385974443543

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f3408242c8f86f2f0dd795382d963178297b08dd3f93849ff3d982f28c220e
+size 1112197096

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": 512,
+  "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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}