Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,88 @@
+---
+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 11371 with parameters:
+```
+{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.OnlineContrastiveLoss.OnlineContrastiveLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 8,
+    "evaluation_steps": 0,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "warmuplinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 10000,
+    "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': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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 +1,32 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/BAAI_bge-base-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": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.36.2",
+  "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/binary_classification_evaluation_results.csv

@@ -0,0 +1,9 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
+0,-1,0.8894110663137846,0.8726729154586792,0.853081485301702,0.814739564093092,0.8952103910161007,0.863213300704956,0.8974880874953977,0.8889905760716318,11.074914932250977,0.8533814014871085,0.8140006140620203,0.8967663374374238,11.570099830627441,0.8974635036866925,0.8894110663137846,0.5046326518058777,0.853081485301702,0.814739564093092,0.8952103910161007,0.5230423212051392,0.8975743958448185,0.8894110663137846,0.8726729154586792,0.853081485301702,0.814739564093092,0.8952103910161007,0.8632134199142456,0.8974631750450622
+1,-1,0.9000717306883672,0.8647794127464294,0.8678657230049998,0.8343320848938827,0.9042078203220133,0.8561683893203735,0.913514950622972,0.899750179326721,11.650308609008789,0.8675159648610976,0.8328250451235452,0.9052225679880936,11.875024795532227,0.9135494898711622,0.9000717306883672,0.5200395584106445,0.8678657230049998,0.8343320848938827,0.9042078203220133,0.5363423824310303,0.9136270979496859,0.9000717306883672,0.8647793531417847,0.8678657230049998,0.8343320848938827,0.9042078203220133,0.8561684489250183,0.9135615930066004
+2,-1,0.9045981844715427,0.8679709434509277,0.8726106310552499,0.8452758402029169,0.9017724259234203,0.8619228005409241,0.9182664631857849,0.9045734497514161,11.385364532470703,0.8726089785296032,0.840456197518486,0.9073197131646598,11.72685432434082,0.9182858121348876,0.9045981844715427,0.5138657689094543,0.8726106310552499,0.8452758402029169,0.9017724259234203,0.5255039930343628,0.9183749712496869,0.9045981844715427,0.8679710626602173,0.8726106310552499,0.8452758402029169,0.9017724259234203,0.8619227409362793,0.9183340377592901
+3,-1,0.9063296148804076,0.8731502890586853,0.8760233536645031,0.8458147005101719,0.9084697605195508,0.8660376071929932,0.9215888359128617,0.9064285537609142,11.016427040100098,0.8761563517915311,0.8448925744440257,0.909822757407658,11.455008506774902,0.9215934348778176,0.9063296148804076,0.5036858320236206,0.8760233536645031,0.8458147005101719,0.9084697605195508,0.517614483833313,0.9216842776366039,0.9063296148804076,0.8731503486633301,0.8760233536645031,0.8458147005101719,0.9084697605195508,0.8660376071929932,0.9216146854005058
+4,-1,0.9071953300848401,0.8642836213111877,0.875092960843276,0.8381542273149581,0.9154376944933027,0.843239426612854,0.9219608863490714,0.9069727176037004,11.583162307739258,0.8754039970978168,0.8540540540540541,0.8978487349479096,11.946100234985352,0.9219844364277952,0.9071953300848401,0.5209921598434448,0.875092960843276,0.8381542273149581,0.9154376944933027,0.559929609298706,0.9220771892342658,0.9071953300848401,0.8642836809158325,0.875092960843276,0.8381542273149581,0.9154376944933027,0.843239426612854,0.9219703976581184
+5,-1,0.9090256993742116,0.8728982210159302,0.8785083543971374,0.8533256807601556,0.9052225679880936,0.8636312484741211,0.9243418101254697,0.908926760493705,11.300579071044922,0.8784308563154084,0.8552935144834658,0.9028548234339061,11.466693878173828,0.9243873681520582,0.9090256993742116,0.5041859745979309,0.8785083543971374,0.8533256807601556,0.9052225679880936,0.5222426652908325,0.9244457747214353,0.9090256993742116,0.8728982210159302,0.8785083543971374,0.8533256807601556,0.9052225679880936,0.8636312484741211,0.924384609603758
+6,-1,0.9097677409780108,0.8619492053985596,0.8794529469228264,0.8478151682571572,0.9135434988499527,0.8502360582351685,0.9240219599928648,0.9095203937767444,11.501441955566406,0.8793131483950697,0.8466837853071961,0.914558246516033,12.112016677856445,0.9240483764870904,0.9097677409780108,0.5254536271095276,0.8794529469228264,0.8478151682571572,0.9135434988499527,0.5472913980484009,0.9241222123353483,0.9097677409780108,0.8619492053985596,0.8794529469228264,0.8478151682571572,0.9135434988499527,0.850236177444458,0.9240385030261205
+7,-1,0.9099903534591506,0.8681730031967163,0.8798801732278336,0.8482013936844749,0.9140170477607902,0.852232813835144,0.9248234406964589,0.9101387617799105,11.39983081817627,0.8795641740709514,0.8446686596910812,0.9174671898254634,12.09014892578125,0.9248780629159912,0.9099903534591506,0.5134725570678711,0.8798801732278336,0.8482013936844749,0.9140170477607902,0.5436307787895203,0.9249197879998878,0.9099903534591506,0.8681729435920715,0.8798801732278336,0.8482013936844749,0.9140170477607902,0.852232813835144,0.9247845722254051

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:242bffd6baa3e536452adf44b5e8832f8f3e7dcff910479608ff6b924f9f93f9
+size 437951328

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]"
+}