Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}

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 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 99 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": 2,
+    "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": 19,
+    "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': 384, '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})
+  (2): Normalize()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "BAAI/bge-small-en",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.28.1",
+    "pytorch": "1.13.0+cu117"
+  }
+}

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,-1,0.7272727272727273,0.8636363636363636,0.9545454545454546,1.0,0.7272727272727273,0.7272727272727273,0.2878787878787878,0.8636363636363636,0.19090909090909094,0.9545454545454546,0.10000000000000003,1.0,0.8058080808080806,0.852249505206517,0.805808080808081,0.7272727272727273,0.8636363636363636,0.9545454545454546,1.0,0.7272727272727273,0.7272727272727273,0.2878787878787878,0.8636363636363636,0.19090909090909094,0.9545454545454546,0.10000000000000003,1.0,0.8058080808080806,0.852249505206517,0.805808080808081
+1,-1,0.6818181818181818,0.8636363636363636,0.9545454545454546,1.0,0.6818181818181818,0.6818181818181818,0.2878787878787878,0.8636363636363636,0.19090909090909094,0.9545454545454546,0.10000000000000003,1.0,0.783080808080808,0.8354735849143105,0.7830808080808083,0.6818181818181818,0.8636363636363636,0.9545454545454546,1.0,0.6818181818181818,0.6818181818181818,0.2878787878787878,0.8636363636363636,0.19090909090909094,0.9545454545454546,0.10000000000000003,1.0,0.783080808080808,0.8354735849143105,0.7830808080808083
+0,50,0.35365853658536583,0.7723577235772358,0.8414634146341463,0.9024390243902439,0.35365853658536583,0.17682926829268292,0.25745257452574527,0.3861788617886179,0.16829268292682925,0.42073170731707316,0.0902439024390244,0.45121951219512196,0.5791198864369597,0.40467193461960477,0.29156911996718043,0.35365853658536583,0.7723577235772358,0.8414634146341463,0.9024390243902439,0.35365853658536583,0.17682926829268292,0.25745257452574527,0.3861788617886179,0.16829268292682925,0.42073170731707316,0.0902439024390244,0.45121951219512196,0.5791198864369597,0.40467193461960477,0.29156911996718043
+0,-1,0.35365853658536583,0.7804878048780488,0.8577235772357723,0.9186991869918699,0.35365853658536583,0.17682926829268292,0.2601626016260163,0.3902439024390244,0.17154471544715447,0.42886178861788615,0.091869918699187,0.45934959349593496,0.5857352561620855,0.41018396863834106,0.2944554992786015,0.35365853658536583,0.7804878048780488,0.8577235772357723,0.9186991869918699,0.35365853658536583,0.17682926829268292,0.2601626016260163,0.3902439024390244,0.17154471544715447,0.42886178861788615,0.091869918699187,0.45934959349593496,0.5857352561620855,0.41018396863834106,0.2944554992786015
+1,50,0.34959349593495936,0.7764227642276422,0.8536585365853658,0.9227642276422764,0.34959349593495936,0.17479674796747968,0.25880758807588083,0.3882113821138211,0.17073170731707318,0.4268292682926829,0.09227642276422765,0.4613821138211382,0.5819073428829529,0.4088719332187641,0.29238317508053707,0.34959349593495936,0.7764227642276422,0.8536585365853658,0.9227642276422764,0.34959349593495936,0.17479674796747968,0.25880758807588083,0.3882113821138211,0.17073170731707318,0.4268292682926829,0.09227642276422765,0.4613821138211382,0.5819073428829529,0.4088719332187641,0.29238317508053707
+1,-1,0.35772357723577236,0.7845528455284553,0.8577235772357723,0.9227642276422764,0.35772357723577236,0.17886178861788618,0.2615176151761518,0.39227642276422764,0.17154471544715447,0.42886178861788615,0.09227642276422765,0.4613821138211382,0.5877064782552589,0.4115902825995784,0.2953281451780637,0.35772357723577236,0.7845528455284553,0.8577235772357723,0.9227642276422764,0.35772357723577236,0.17886178861788618,0.2615176151761518,0.39227642276422764,0.17154471544715447,0.42886178861788615,0.09227642276422765,0.4613821138211382,0.5877064782552589,0.4115902825995784,0.2953281451780637
+0,50,0.35365853658536583,0.7723577235772358,0.8414634146341463,0.9065040650406504,0.35365853658536583,0.17682926829268292,0.25745257452574527,0.3861788617886179,0.16829268292682925,0.42073170731707316,0.09065040650406504,0.4532520325203252,0.5791811846689897,0.40527819888955446,0.2913175110321673,0.35365853658536583,0.7723577235772358,0.8414634146341463,0.9065040650406504,0.35365853658536583,0.17682926829268292,0.25745257452574527,0.3861788617886179,0.16829268292682925,0.42073170731707316,0.09065040650406504,0.4532520325203252,0.5791811846689897,0.40527819888955446,0.2913175110321673
+0,-1,0.34552845528455284,0.7723577235772358,0.8577235772357723,0.9146341463414634,0.34552845528455284,0.17276422764227642,0.25745257452574527,0.3861788617886179,0.17154471544715444,0.42886178861788615,0.09146341463414634,0.4573170731707317,0.5791311782165443,0.406543818927041,0.29123770467261045,0.34552845528455284,0.7723577235772358,0.8577235772357723,0.9146341463414634,0.34552845528455284,0.17276422764227642,0.25745257452574527,0.3861788617886179,0.17154471544715444,0.42886178861788615,0.09146341463414634,0.4573170731707317,0.5791311782165443,0.406543818927041,0.29123770467261045
+1,50,0.34959349593495936,0.7723577235772358,0.8495934959349594,0.9186991869918699,0.34959349593495936,0.17479674796747968,0.25745257452574527,0.3861788617886179,0.16991869918699185,0.4247967479674797,0.091869918699187,0.45934959349593496,0.5821009162472577,0.4083924003073017,0.2925662078782343,0.34959349593495936,0.7723577235772358,0.8495934959349594,0.9186991869918699,0.34959349593495936,0.17479674796747968,0.25745257452574527,0.3861788617886179,0.16991869918699185,0.4247967479674797,0.091869918699187,0.45934959349593496,0.5821009162472577,0.4083924003073017,0.2925662078782343
+1,-1,0.34552845528455284,0.7682926829268293,0.8495934959349594,0.9186991869918699,0.34552845528455284,0.17276422764227642,0.2560975609756098,0.38414634146341464,0.16991869918699185,0.4247967479674797,0.091869918699187,0.45934959349593496,0.5783955994321849,0.4066643884523926,0.29075655615322343,0.34552845528455284,0.7682926829268293,0.8495934959349594,0.9186991869918699,0.34552845528455284,0.17276422764227642,0.2560975609756098,0.38414634146341464,0.16991869918699185,0.4247967479674797,0.091869918699187,0.45934959349593496,0.5783955994321849,0.4066643884523926,0.29075655615322343

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceaaa7335c45f231c248c3dbb211e5fd3c2041ac10b937e0a989a07eb1f9af1e
+size 133462128

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]"
+}