Adds all files except tensors

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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

@@ -1,3 +1,92 @@
 ---
-license: mit
+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 1024 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 200 with parameters:
+```
+{'batch_size': 8, '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": 5,
+    "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": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-large-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "1.13.0+cu117"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

eval/Information-Retrieval_evaluation_results.csv

@@ -0,0 +1,26 @@
+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
+0,50,0.89,0.96,0.98,0.995,0.89,0.89,0.32,0.96,0.196,0.98,0.09949999999999999,0.995,0.9299851190476189,0.946048402252211,0.9302884278711485,0.89,0.96,0.98,0.995,0.89,0.89,0.32,0.96,0.196,0.98,0.09949999999999999,0.995,0.9299851190476189,0.946048402252211,0.9302884278711485
+0,100,0.905,0.975,0.9825,0.9975,0.905,0.905,0.325,0.975,0.19649999999999998,0.9825,0.09974999999999999,0.9975,0.9402976190476191,0.9544146141940891,0.9405059523809524,0.905,0.975,0.9825,0.9975,0.905,0.905,0.325,0.975,0.19649999999999998,0.9825,0.09974999999999999,0.9975,0.9402976190476191,0.9544146141940891,0.9405059523809524
+0,150,0.9025,0.9625,0.975,0.9975,0.9025,0.9025,0.3208333333333333,0.9625,0.195,0.975,0.09974999999999999,0.9975,0.9361825396825398,0.9510492429888154,0.9364098124098124,0.9025,0.9625,0.975,0.9975,0.9025,0.9025,0.3208333333333333,0.9625,0.195,0.975,0.09974999999999999,0.9975,0.9361825396825398,0.9510492429888154,0.9364098124098124
+0,200,0.89,0.9675,0.98,0.9975,0.89,0.89,0.3225,0.9675,0.196,0.98,0.09974999999999999,0.9975,0.9290932539682539,0.9458279004537382,0.9292855616605619,0.89,0.9675,0.98,0.9975,0.89,0.89,0.3225,0.9675,0.196,0.98,0.09974999999999999,0.9975,0.9290932539682539,0.9458279004537382,0.9292855616605619
+0,-1,0.89,0.9675,0.98,0.9975,0.89,0.89,0.3225,0.9675,0.196,0.98,0.09974999999999999,0.9975,0.9290932539682539,0.9458279004537382,0.9292855616605619,0.89,0.9675,0.98,0.9975,0.89,0.89,0.3225,0.9675,0.196,0.98,0.09974999999999999,0.9975,0.9290932539682539,0.9458279004537382,0.9292855616605619
+1,50,0.8975,0.975,0.9825,0.9975,0.8975,0.8975,0.325,0.975,0.19649999999999998,0.9825,0.09974999999999999,0.9975,0.9374186507936507,0.9523397329756622,0.9375436507936508,0.8975,0.975,0.9825,0.9975,0.8975,0.8975,0.325,0.975,0.19649999999999998,0.9825,0.09974999999999999,0.9975,0.9374186507936507,0.9523397329756622,0.9375436507936508
+1,100,0.895,0.9625,0.98,0.995,0.895,0.895,0.3208333333333333,0.9625,0.196,0.98,0.09949999999999999,0.995,0.933252976190476,0.9485028339597544,0.9336725566100565,0.895,0.9625,0.98,0.995,0.895,0.895,0.3208333333333333,0.9625,0.196,0.98,0.09949999999999999,0.995,0.933252976190476,0.9485028339597544,0.9336725566100565
+1,150,0.89,0.9575,0.97,0.9975,0.89,0.89,0.31916666666666665,0.9575,0.19399999999999998,0.97,0.09974999999999999,0.9975,0.9280128968253968,0.9448939681024554,0.9281914682539683,0.89,0.9575,0.97,0.9975,0.89,0.89,0.31916666666666665,0.9575,0.19399999999999998,0.97,0.09974999999999999,0.9975,0.9280128968253968,0.9448939681024554,0.9281914682539683
+1,200,0.8825,0.9575,0.97,0.99,0.8825,0.8825,0.31916666666666665,0.9575,0.19399999999999998,0.97,0.09899999999999999,0.99,0.9219126984126984,0.9386255118831167,0.9226414592352091,0.8825,0.9575,0.97,0.99,0.8825,0.8825,0.31916666666666665,0.9575,0.19399999999999998,0.97,0.09899999999999999,0.99,0.9219126984126984,0.9386255118831167,0.9226414592352091
+1,-1,0.8825,0.9575,0.97,0.99,0.8825,0.8825,0.31916666666666665,0.9575,0.19399999999999998,0.97,0.09899999999999999,0.99,0.9219126984126984,0.9386255118831167,0.9226414592352091,0.8825,0.9575,0.97,0.99,0.8825,0.8825,0.31916666666666665,0.9575,0.19399999999999998,0.97,0.09899999999999999,0.99,0.9219126984126984,0.9386255118831167,0.9226414592352091
+2,50,0.885,0.955,0.9775,0.995,0.885,0.885,0.3183333333333333,0.955,0.19549999999999998,0.9775,0.09949999999999999,0.995,0.9255267857142857,0.9425716941814793,0.9258190934065934,0.885,0.955,0.9775,0.995,0.885,0.885,0.3183333333333333,0.955,0.19549999999999998,0.9775,0.09949999999999999,0.995,0.9255267857142857,0.9425716941814793,0.9258190934065934
+2,100,0.8775,0.9625,0.9775,0.99,0.8775,0.8775,0.3208333333333333,0.9625,0.19549999999999998,0.9775,0.09899999999999999,0.99,0.9221488095238094,0.9390513628815879,0.9228701298701298,0.8775,0.9625,0.9775,0.99,0.8775,0.8775,0.3208333333333333,0.9625,0.19549999999999998,0.9775,0.09899999999999999,0.99,0.9221488095238094,0.9390513628815879,0.9228701298701298
+2,150,0.895,0.9675,0.9725,0.9925,0.895,0.895,0.3225,0.9675,0.1945,0.9725,0.09924999999999999,0.9925,0.9337242063492064,0.9482915798717261,0.9342198228650435,0.895,0.9675,0.9725,0.9925,0.895,0.895,0.3225,0.9675,0.1945,0.9725,0.09924999999999999,0.9925,0.9337242063492064,0.9482915798717261,0.9342198228650435
+2,200,0.8925,0.965,0.9725,0.9925,0.8925,0.8925,0.3216666666666667,0.965,0.1945,0.9725,0.09924999999999999,0.9925,0.9294474206349205,0.9449308919116254,0.9299968711843712,0.8925,0.965,0.9725,0.9925,0.8925,0.8925,0.3216666666666667,0.965,0.1945,0.9725,0.09924999999999999,0.9925,0.9294474206349205,0.9449308919116254,0.9299968711843712
+2,-1,0.8925,0.965,0.9725,0.9925,0.8925,0.8925,0.3216666666666667,0.965,0.1945,0.9725,0.09924999999999999,0.9925,0.9294474206349205,0.9449308919116254,0.9299968711843712,0.8925,0.965,0.9725,0.9925,0.8925,0.8925,0.3216666666666667,0.965,0.1945,0.9725,0.09924999999999999,0.9925,0.9294474206349205,0.9449308919116254,0.9299968711843712
+3,50,0.9,0.9675,0.98,0.9925,0.9,0.9,0.3225,0.9675,0.196,0.98,0.09924999999999999,0.9925,0.9352321428571427,0.9493751042740257,0.9357217261904762,0.9,0.9675,0.98,0.9925,0.9,0.9,0.3225,0.9675,0.196,0.98,0.09924999999999999,0.9925,0.9352321428571427,0.9493751042740257,0.9357217261904762
+3,100,0.89,0.97,0.9825,0.9925,0.89,0.89,0.3233333333333333,0.97,0.19649999999999998,0.9825,0.09924999999999999,0.9925,0.9327113095238095,0.947732452432563,0.9332069260396466,0.89,0.97,0.9825,0.9925,0.89,0.89,0.3233333333333333,0.97,0.19649999999999998,0.9825,0.09924999999999999,0.9925,0.9327113095238095,0.947732452432563,0.9332069260396466
+3,150,0.89,0.9675,0.985,0.9925,0.89,0.89,0.3225,0.9675,0.19699999999999998,0.985,0.09924999999999999,0.9925,0.930735119047619,0.9461597163308143,0.9313213661338662,0.89,0.9675,0.985,0.9925,0.89,0.89,0.3225,0.9675,0.19699999999999998,0.985,0.09924999999999999,0.9925,0.930735119047619,0.9461597163308143,0.9313213661338662
+3,200,0.88,0.9625,0.9825,0.995,0.88,0.88,0.3208333333333333,0.9625,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9248988095238093,0.9422868897699794,0.9252473672161173,0.88,0.9625,0.9825,0.995,0.88,0.88,0.3208333333333333,0.9625,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9248988095238093,0.9422868897699794,0.9252473672161173
+3,-1,0.88,0.9625,0.9825,0.995,0.88,0.88,0.3208333333333333,0.9625,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9248988095238093,0.9422868897699794,0.9252473672161173,0.88,0.9625,0.9825,0.995,0.88,0.88,0.3208333333333333,0.9625,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9248988095238093,0.9422868897699794,0.9252473672161173
+4,50,0.8825,0.965,0.9825,0.995,0.8825,0.8825,0.32166666666666666,0.965,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9267738095238093,0.943710198374796,0.9271327838827839,0.8825,0.965,0.9825,0.995,0.8825,0.8825,0.32166666666666666,0.965,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9267738095238093,0.943710198374796,0.9271327838827839
+4,100,0.8775,0.9675,0.985,0.995,0.8775,0.8775,0.3225,0.9675,0.19699999999999998,0.985,0.09949999999999999,0.995,0.924565476190476,0.9421147697977861,0.9249244505494505,0.8775,0.9675,0.985,0.995,0.8775,0.8775,0.3225,0.9675,0.19699999999999998,0.985,0.09949999999999999,0.995,0.924565476190476,0.9421147697977861,0.9249244505494505
+4,150,0.8725,0.9675,0.9825,0.995,0.8725,0.8725,0.3225,0.9675,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9224236111111108,0.9405412263308881,0.9227688492063493,0.8725,0.9675,0.9825,0.995,0.8725,0.8725,0.3225,0.9675,0.19649999999999998,0.9825,0.09949999999999999,0.995,0.9224236111111108,0.9405412263308881,0.9227688492063493
+4,200,0.8725,0.9675,0.9825,0.9925,0.8725,0.8725,0.3225,0.9675,0.19649999999999998,0.9825,0.09924999999999999,0.9925,0.9225902777777776,0.940145888649022,0.9231438492063492,0.8725,0.9675,0.9825,0.9925,0.8725,0.8725,0.3225,0.9675,0.19649999999999998,0.9825,0.09924999999999999,0.9925,0.9225902777777776,0.940145888649022,0.9231438492063492
+4,-1,0.8725,0.9675,0.9825,0.9925,0.8725,0.8725,0.3225,0.9675,0.19649999999999998,0.9825,0.09924999999999999,0.9925,0.9225902777777776,0.940145888649022,0.9231438492063492,0.8725,0.9675,0.9825,0.9925,0.8725,0.8725,0.3225,0.9675,0.19649999999999998,0.9825,0.09924999999999999,0.9925,0.9225902777777776,0.940145888649022,0.9231438492063492

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": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}