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
+vocab.txt filter=lfs diff=lfs merge=lfs -text

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 +1,126 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {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)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+def cls_pooling(model_output, attention_mask):
+    return model_output[0][:,0]
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, cls pooling.
+sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_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: 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})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "dicta-il/dictabert",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "newmodern": true,
+  "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": 128000
+}

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": 0.5552091079576894}, {"epoch": 1, "loss": 0.14668889793562054}, {"epoch": 2, "loss": 0.03926950940472795}]}

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
+0,500,0.9357277882797732,0.5196293592453003,0.9356060606060606,0.9285714285714286,0.9427480916030534,0.5196293592453003,0.9742855284077233,0.9357277882797732,343.64703369140625,0.9354838709677419,0.930188679245283,0.9408396946564885,348.995361328125,0.9764954223498737,0.9357277882797732,16.496044158935547,0.9356060606060606,0.9285714285714286,0.9427480916030534,16.496044158935547,0.976002940633654,0.9310018903591682,144.704345703125,0.9313264346190029,0.9183673469387755,0.9446564885496184,144.704345703125,0.9657047063732095
+0,1000,0.9328922495274102,0.4960457980632782,0.9334582942830365,0.9171270718232044,0.950381679389313,0.4960457980632782,0.9775104352100861,0.9347826086956522,352.5271911621094,0.9355742296918768,0.9159049360146252,0.9561068702290076,364.15960693359375,0.9798455746293088,0.9385633270321361,17.329761505126953,0.9390815370196813,0.9226519337016574,0.9561068702290076,17.329761505126953,0.9795656100996063,0.9262759924385633,145.15023803710938,0.9273229070837167,0.8952042628774423,0.9618320610687023,134.46905517578125,0.9704276692608728
+0,-1,0.9366729678638941,0.4899904131889343,0.9370892018779342,0.922365988909427,0.9522900763358778,0.4899904131889343,0.9743229436211243,0.9385633270321361,361.84490966796875,0.9398704902867715,0.9120287253141831,0.9694656488549618,381.13848876953125,0.9768196593404925,0.9404536862003781,17.394351959228516,0.94062205466541,0.9292364990689013,0.9522900763358778,17.394351959228516,0.9770181914372765,0.9347826086956522,147.9871368408203,0.9352112676056338,0.9205175600739371,0.950381679389313,147.9871368408203,0.9621333877078682
+1,500,0.9404536862003781,0.4546582102775574,0.941066417212348,0.9229357798165138,0.9599236641221374,0.4546582102775574,0.979020052998192,0.943289224952741,382.796875,0.9443413729128015,0.9187725631768953,0.9713740458015268,384.9874572753906,0.9809352479972135,0.941398865784499,18.785140991210938,0.9431192660550459,0.9081272084805654,0.9809160305343512,19.05669403076172,0.9805054188156175,0.9376181474480151,129.74554443359375,0.9388888888888889,0.9118705035971223,0.9675572519083969,129.74554443359375,0.9727834883885278
+1,1000,0.94234404536862,0.4975280463695526,0.9419600380589915,0.9392789373814042,0.9446564885496184,0.48240917921066284,0.9842468127351804,0.946124763705104,362.0586242675781,0.9455587392550143,0.9464627151051626,0.9446564885496184,362.0586242675781,0.9857615586624637,0.947069943289225,17.691368103027344,0.9465648854961832,0.9465648854961832,0.9465648854961832,17.691368103027344,0.9857418511931075,0.9385633270321361,147.11984252929688,0.9386213408876298,0.9289719626168225,0.9484732824427481,141.555908203125,0.9795327664680187
+1,-1,0.9489603024574669,0.42314964532852173,0.949438202247191,0.9319852941176471,0.9675572519083969,0.42314964532852173,0.9872732814993084,0.9508506616257089,380.796630859375,0.9508506616257089,0.9419475655430711,0.9599236641221374,380.796630859375,0.9885179108890427,0.9499054820415879,18.473026275634766,0.9501411100658514,0.9369202226345084,0.9637404580152672,18.539331436157227,0.988287040911294,0.947069943289225,124.73574829101562,0.9478584729981377,0.9254545454545454,0.9713740458015268,123.55701446533203,0.9840364744375375
+2,500,0.941398865784499,0.37280166149139404,0.9431192660550459,0.9081272084805654,0.9809160305343512,0.37280166149139404,0.9846145262965152,0.944234404536862,396.7467041015625,0.9456221198156682,0.9144385026737968,0.9790076335877863,396.7467041015625,0.9864332319474167,0.945179584120983,19.376388549804688,0.9464944649446494,0.9160714285714285,0.9790076335877863,19.376388549804688,0.9859387719578248,0.941398865784499,121.46650695800781,0.9429097605893185,0.9110320284697508,0.9770992366412213,121.46650695800781,0.9793170511018084
+2,1000,0.941398865784499,0.4293143153190613,0.9421641791044776,0.9215328467153284,0.9637404580152672,0.4272366762161255,0.9833760894408956,0.946124763705104,376.1376037597656,0.946073793755913,0.9380863039399625,0.9541984732824428,376.1376037597656,0.9856706557044219,0.943289224952741,18.11858558654785,0.9436749769159742,0.9141323792486583,0.9751908396946565,19.424821853637695,0.985209911755514,0.9366729678638941,132.0089111328125,0.9375582479030755,0.9162112932604736,0.9599236641221374,132.0089111328125,0.9767609071017523
+2,-1,0.944234404536862,0.4578818082809448,0.9444967074317969,0.9313543599257885,0.9580152671755725,0.4498842656612396,0.9848264672647637,0.946124763705104,370.8468322753906,0.9464788732394366,0.9316081330868762,0.9618320610687023,382.0978698730469,0.9868899736668068,0.945179584120983,17.448890686035156,0.9458218549127639,0.911504424778761,0.982824427480916,19.76630210876465,0.9863880902389214,0.9404536862003781,138.0528564453125,0.9407337723424272,0.9276437847866419,0.9541984732824428,138.0528564453125,0.9790914146121825

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4df38204b69dd9d31b93c7de767af4d650fb61d5ae820826e98fd3958a3fef
+size 737403752

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

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 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[BLANK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb90bfa35244d26f0065d1fcd0b5becc3da3d44d616a7e2aacaf6320b9fa2d0
+size 1500244