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": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": true,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,130 @@
+---
+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
+
+
+# Max Pooling - Take the max value over time for every dimension. 
+def max_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    token_embeddings[input_mask_expanded == 0] = -1e9  # Set padding tokens to large negative value
+    return torch.max(token_embeddings, 1)[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, max pooling.
+sentence_embeddings = max_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': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': True, '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": 0.7003634975294062}, {"epoch": 1, "loss": 0.16605059529728186}, {"epoch": 2, "loss": 0.043034195051239794}]}

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
+0,500,0.8988657844990549,0.6572055816650391,0.8972142170989432,0.9032882011605415,0.8912213740458015,0.6572055816650391,0.944560911694943,0.9083175803402647,326.732177734375,0.9068203650336215,0.9129593810444874,0.9007633587786259,326.732177734375,0.9542491234958791,0.9111531190926276,15.141329765319824,0.9087378640776699,0.924901185770751,0.8931297709923665,15.185525894165039,0.9534047230650327,0.8648393194706995,211.80429077148438,0.8679593721144967,0.8407871198568873,0.8969465648854962,211.63311767578125,0.8786261823859223
+0,1000,0.9300567107750473,0.6528611779212952,0.9285714285714285,0.939453125,0.9179389312977099,0.6528611779212952,0.9737300976410953,0.941398865784499,345.21875,0.9406130268199234,0.9442307692307692,0.9370229007633588,345.21875,0.9808658333763999,0.9404536862003781,15.921335220336914,0.9390125847047434,0.9528487229862476,0.9255725190839694,16.045866012573242,0.9806521885152959,0.888468809073724,231.92935180664062,0.8888888888888888,0.8773234200743495,0.9007633587786259,231.92935180664062,0.9083308849892293
+0,-1,0.9243856332703214,0.6674684882164001,0.9227836034318398,0.9219047619047619,0.9236641221374046,0.6389604806900024,0.972027662686941,0.9395085066162571,335.3438720703125,0.938388625592417,0.9322033898305084,0.9446564885496184,348.75653076171875,0.9811218887601132,0.9404536862003781,16.17607879638672,0.938894277400582,0.9546351084812623,0.9236641221374046,16.17607879638672,0.9802486625861153,0.8818525519848771,235.76617431640625,0.8856358645928636,0.8506151142355008,0.9236641221374046,235.76617431640625,0.8797209764276414
+1,500,0.9120982986767486,0.5920199155807495,0.9121813031161473,0.902803738317757,0.9217557251908397,0.5893062353134155,0.9667693463229743,0.9243856332703214,344.0145263671875,0.9233716475095785,0.926923076923077,0.9198473282442748,350.230712890625,0.9749825312208363,0.9243856332703214,17.552833557128906,0.9238095238095239,0.9220532319391636,0.9255725190839694,17.552833557128906,0.9753406657887319,0.8771266540642723,223.262451171875,0.879182156133829,0.8568840579710145,0.9026717557251909,218.62855529785156,0.8911259610239978
+1,1000,0.9206049149338374,0.6353754997253418,0.9184466019417477,0.9347826086956522,0.9026717557251909,0.6248494386672974,0.9725106368499086,0.9404536862003781,359.49932861328125,0.9400570884871551,0.937381404174573,0.9427480916030534,360.86175537109375,0.9812235460956586,0.9395085066162571,18.260955810546875,0.9396226415094339,0.9291044776119403,0.950381679389313,18.32391929626465,0.9807002892852764,0.8856332703213611,235.46749877929688,0.888479262672811,0.8591800356506238,0.9198473282442748,221.70233154296875,0.8993586512879576
+1,-1,0.9111531190926276,0.6492329239845276,0.9089165867689357,0.9132947976878613,0.9045801526717557,0.6242419481277466,0.968144178075093,0.9319470699432892,375.5537109375,0.9329608938547486,0.9109090909090909,0.9561068702290076,375.5537109375,0.9795218545056252,0.9319470699432892,17.96462631225586,0.9322033898305085,0.9200743494423792,0.9446564885496184,17.96462631225586,0.9786044450498129,0.8742911153119093,229.0291748046875,0.8769657724329325,0.8509874326750448,0.9045801526717557,229.0291748046875,0.8709702767617598
+2,500,0.9149338374291115,0.587235152721405,0.9160447761194029,0.8959854014598541,0.9370229007633588,0.5855621695518494,0.9670082558410162,0.9385633270321361,363.227294921875,0.9386213408876298,0.9289719626168225,0.9484732824427481,364.4090576171875,0.9779200733984246,0.9366729678638941,18.57184600830078,0.9375582479030755,0.9162112932604736,0.9599236641221374,18.57184600830078,0.9769772074830768,0.8742911153119093,237.5072479248047,0.8769657724329325,0.8509874326750448,0.9045801526717557,236.1907196044922,0.8710122088055272
+2,1000,0.9196597353497165,0.6004956960678101,0.9198868991517437,0.9087523277467412,0.9312977099236641,0.5983362793922424,0.9711544148164128,0.943289224952741,371.24688720703125,0.9435028248587569,0.9312267657992565,0.9561068702290076,371.24688720703125,0.9811158571018329,0.9404536862003781,18.651973724365234,0.9408450704225352,0.9260628465804066,0.9561068702290076,18.651973724365234,0.9802401197414027,0.8790170132325141,250.70159912109375,0.8802946593001842,0.8505338078291815,0.9122137404580153,233.8839874267578,0.8766882017532465
+2,-1,0.9215500945179584,0.6059660911560059,0.9219330855018587,0.8985507246376812,0.9465648854961832,0.5740522146224976,0.9718580893477863,0.945179584120983,372.1387023925781,0.9452830188679245,0.9347014925373134,0.9561068702290076,372.1387023925781,0.9815518873468673,0.94234404536862,18.611305236816406,0.9427230046948356,0.9279112754158965,0.9580152671755725,18.611305236816406,0.9807262410767907,0.8818525519848771,247.81253051757812,0.8830935251798561,0.8350340136054422,0.9370229007633588,220.95921325683594,0.8813355917517796

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd958577210a765e760d0cc0afcafe1e4ffd0dfd916e589961a53e480d711ed
+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