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 +1,7 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,91 @@
+---
+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 1229 with parameters:
+```
+{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.TripletLoss.TripletLoss` with parameters:
+  ```
+  {'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 3,
+    "evaluation_steps": 500,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 3e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 50,
+    "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': 1024, '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": "/home/azureuser/.cache/torch/sentence_transformers/intfloat_multilingual-e5-large/",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.36.2",
+    "pytorch": "2.1.2+cu121"
+  }
+}

epoch_losses.json

@@ -0,0 +1 @@
+{"log_history": [{"epoch": 0, "loss": 4.241837462145105}, {"epoch": 1, "loss": 4.103551355195879}, {"epoch": 2, "loss": 3.998317237012846}]}

eval/binary_classification_evaluation_results.csv

@@ -0,0 +1,10 @@
+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
+0,500,0.781663516068053,0.9829764366149902,0.7884108867427568,0.7300813008130081,0.8568702290076335,0.8545087575912476,0.8643439417220432,0.781663516068053,4.758382797241211,0.7876651982378854,0.7315875613747954,0.8530534351145038,13.004348754882812,0.8635710405078184,0.781663516068053,0.1845133751630783,0.7884108867427568,0.7300813008130081,0.8568702290076335,0.5394230484962463,0.8643439417220432,0.781663516068053,0.9829764366149902,0.7884108867427568,0.7300813008130081,0.8568702290076335,0.8545088171958923,0.864344165843822
+0,1000,0.7930056710775047,0.8264037370681763,0.804251550044287,0.7504132231404959,0.8664122137404581,0.758542001247406,0.883202705974117,0.7930056710775047,15.233765602111816,0.804251550044287,0.7504132231404959,0.8664122137404581,17.948760986328125,0.8828002010939948,0.7930056710775047,0.5892293453216553,0.804251550044287,0.7504132231404959,0.8664122137404581,0.6949169635772705,0.883202705974117,0.7930056710775047,0.826403796672821,0.804251550044287,0.7504132231404959,0.8664122137404581,0.758542001247406,0.8832029444939204
+0,-1,0.7646502835538752,0.6711565256118774,0.7996781979082865,0.6912378303198887,0.9484732824427481,0.6711565256118774,0.8087048393898709,0.7646502835538752,21.16190528869629,0.7996781979082865,0.6912378303198887,0.9484732824427481,21.16190528869629,0.8084139669836443,0.7646502835538752,0.8109352588653564,0.7996781979082865,0.6912378303198887,0.9484732824427481,0.8109352588653564,0.8086994645011314,0.7646502835538752,0.6711565256118774,0.7996781979082865,0.6912378303198887,0.9484732824427481,0.6711565256118774,0.8086847813164357
+1,500,0.781663516068053,0.9758460521697998,0.7825327510917031,0.7214170692431562,0.8549618320610687,0.7405884265899658,0.8550805541631465,0.781663516068053,5.615372657775879,0.7845884413309984,0.7249190938511327,0.8549618320610687,18.531112670898438,0.8551786077926244,0.781663516068053,0.21978893876075745,0.7825327510917031,0.7214170692431562,0.8549618320610687,0.7202937602996826,0.8551273002775579,0.781663516068053,0.9758461713790894,0.7825327510917031,0.7214170692431562,0.8549618320610687,0.7405884265899658,0.8550533275581665
+1,1000,0.8034026465028355,0.960740327835083,0.8007626310772165,0.8,0.8015267175572519,0.9258443117141724,0.8821783210679962,0.8034026465028355,7.276186943054199,0.8011417697431018,0.7988614800759013,0.8034351145038168,10.180410385131836,0.8825871472333959,0.8034026465028355,0.2802126705646515,0.8007626310772165,0.8,0.8015267175572519,0.38510599732398987,0.8821783210679961,0.8034026465028355,0.960740327835083,0.8007626310772165,0.8,0.8015267175572519,0.9258443117141724,0.8821783210679962
+1,-1,0.7996219281663516,0.9835190773010254,0.783484390735146,0.8294243070362474,0.7423664122137404,0.9617328643798828,0.8697700141500904,0.7996219281663516,5.322716236114502,0.7842741935483871,0.8311965811965812,0.7423664122137404,7.225118160247803,0.8702594922363502,0.7996219281663516,0.18154972791671753,0.783484390735146,0.8294243070362474,0.7423664122137404,0.2766408324241638,0.8697700141500904,0.7996219281663516,0.9835190773010254,0.783484390735146,0.8294243070362474,0.7423664122137404,0.9617329239845276,0.8697700141500904
+2,500,0.8109640831758034,0.9721739292144775,0.7991967871485944,0.8432203389830508,0.7595419847328244,0.9613770246505737,0.8782081110264903,0.8119092627599244,6.24746036529541,0.8,0.8403361344537815,0.7633587786259542,7.858887195587158,0.8792454962617684,0.8109640831758034,0.23590686917304993,0.7991967871485944,0.8432203389830508,0.7595419847328244,0.2779298424720764,0.8782075238602783,0.8109640831758034,0.9721739292144775,0.7991967871485944,0.8432203389830508,0.7595419847328244,0.9613770246505737,0.8782084073773831
+2,1000,0.8062381852551985,0.9575773477554321,0.8069216757741349,0.7717770034843205,0.8454198473282443,0.8217760324478149,0.874437013442052,0.8081285444234405,7.59599494934082,0.8069216757741349,0.7717770034843205,0.8454198473282443,15.570981979370117,0.8745057954947547,0.8062381852551985,0.2912757098674774,0.8069216757741349,0.7717770034843205,0.8454198473282443,0.5969957113265991,0.8744364803702791,0.8062381852551985,0.9575772881507874,0.8069216757741349,0.7717770034843205,0.8454198473282443,0.8217760324478149,0.8744308798833125
+2,-1,0.8081285444234405,0.9606646299362183,0.8081343943412909,0.7528830313014827,0.8721374045801527,0.6946588754653931,0.8757539100677689,0.8081285444234405,7.314235687255859,0.8090452261306531,0.7208955223880597,0.9217557251908397,28.974647521972656,0.8756947408460566,0.8081285444234405,0.2804830074310303,0.8081343943412909,0.7528830313014827,0.8721374045801527,0.7814613580703735,0.8757532844459008,0.8081285444234405,0.9606646299362183,0.8081343943412909,0.7528830313014827,0.8721374045801527,0.6946588754653931,0.8757539100677689

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222b30620ee620fa2e6ddde1f9149894d72a5b5d2a5872f4a0685855bbbe931f
+size 2239607176

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:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
+size 17083009

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}