Upload 13 files

1_Pooling/config.json

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

README.md

@@ -1,3 +1,136 @@
 ---
-license: cc-by-nc-4.0
+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
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_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()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# 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, mean pooling.
+sentence_embeddings = mean_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 6033 with parameters:
+```
+{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 5765 with parameters:
+```
+{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 0,
+    "evaluator": "sentence_transformers.evaluation.BinaryClassificationEvaluator.BinaryClassificationEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.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': 256, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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": "roberta-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.18.0",
+    "pytorch": "1.11.0"
+  }
+}

eval/binary_classification_evaluation_Valid_Topic_Boundaries_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhatten_accuracy,manhatten_accuracy_threshold,manhatten_f1,manhatten_precision,manhatten_recall,manhatten_f1_threshold,manhatten_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,-1,0.8724363792548051,-0.4885462522506714,0.9315210505097046,0.8746721466619798,0.9962733684437464,-0.5198167562484741,0.9482870767152217,0.8815634059916246,475.5308837890625,0.9356532392147713,0.888633404438042,0.9879269457020543,475.8710632324219,0.9523934225130386,0.8756845270052614,25.743106842041016,0.9327036256630097,0.8829582347438508,0.9883889248205981,25.743106842041016,0.9486990778147659,0.874261784602169,-103.4189453125,0.9323140949683534,0.8782021615441157,0.9935322923403862,-103.4189453125,0.945713013926162
+1,-1,0.8715773649736926,-0.8653514385223389,0.9313826735513483,0.8716007623956404,0.9999692013920971,-0.8653514385223389,0.9406942729659287,0.8791742725222806,520.5626220703125,0.9345224262142692,0.8843013826658237,0.990791216237026,539.4521484375,0.9498210302666706,0.8720874047031032,39.98064422607422,0.9315481748574221,0.8729470680092618,0.9985832640364656,39.98064422607422,0.9400555719254167,0.871657897562547,-295.98388671875,0.9314247192300521,0.8716510067114094,1.0,-435.1869812011719,0.936878204714809
+2,-1,0.871657897562547,-0.8735333681106567,0.9314109461301198,0.8717907401439468,0.9997844097446795,-0.8735333681106567,0.9321755298271551,0.876758294856652,599.8697509765625,0.9335456321922269,0.8806805767970286,0.9931627090455512,599.8697509765625,0.9445760392019119,0.8716847417588317,47.64161682128906,0.9314282435301544,0.8717742152044899,0.9998460069604854,47.64161682128906,0.9333497223616692,0.871657897562547,-541.7020263671875,0.9314247192300521,0.8716510067114094,1.0,-547.5809936523438,0.9255973081265415
+3,-1,0.8716847417588317,-0.8504114151000977,0.9314361122267485,0.8716943646468172,0.9999692013920971,-0.898491382598877,0.9321154275057468,0.8745570707613014,606.3648681640625,0.9324413753416775,0.8748953861936772,0.9980904863100187,645.5669555664062,0.944834245947181,0.8716847417588317,48.6949462890625,0.9314262760737957,0.8717941832048769,0.9998152083525824,48.6949462890625,0.9358121899237093,0.8716847417588317,-567.5224609375,0.9314361122267485,0.8716943646468172,0.9999692013920971,-567.5224609375,0.9199484899635636
+4,-1,0.8716310533662622,-0.8704615235328674,0.9313877410468319,0.8718671931662503,0.999630416705165,-0.8704615235328674,0.9302681043990398,0.8764361645012348,624.4132690429688,0.9333140334370702,0.880462093074066,0.9929163201823278,641.5534057617188,0.9402572160452738,0.8716847417588317,49.69243621826172,0.9314380791187354,0.8716744073666407,1.0,49.69243621826172,0.9328739446647275,0.871657897562547,-561.347412109375,0.9314247192300521,0.8716510067114094,1.0,-588.161376953125,0.9184166581589492
+5,-1,0.8716847417588317,-0.8523590564727783,0.9314148818660432,0.8717508055853921,0.9998460069604854,-0.8868223428726196,0.9307782643507979,0.8750939546869967,646.148681640625,0.9327749295978048,0.8781542310202306,0.9946410422248915,655.21923828125,0.9390805040751276,0.8716310533662622,48.66355895996094,0.9314074244075965,0.8716675168469944,0.9999384027841941,48.66355895996094,0.9337836096373169,0.8716310533662622,-555.56787109375,0.9314113597246128,0.8716276073125554,1.0,-572.7196044921875,0.9173812233431777
+6,-1,0.8717115859551166,-0.8353337049484253,0.9314341452219067,0.871714324070345,0.9999384027841941,-0.8730157613754272,0.9318065746498914,0.8736712122839042,687.2959594726562,0.9321706543672529,0.8760803012652055,0.9959345837568142,687.2959594726562,0.9384547883542511,0.871657897562547,47.198280334472656,0.9314207846231083,0.8716909198303173,0.9999384027841941,47.198280334472656,0.9345394143691392,0.8716310533662622,-509.2225646972656,0.9314113597246128,0.8716276073125554,1.0,-539.64306640625,0.9210116283711751
+7,-1,0.8718458069365403,-0.8367456793785095,0.931487591450294,0.8718079535995275,0.9999384027841941,-0.8653423190116882,0.9253199547135915,0.8732148609470632,719.7484130859375,0.9320765019470347,0.8736396939984915,0.9988912501154947,733.858154296875,0.9313230885505059,0.8716847417588317,46.59550094604492,0.9314361122267485,0.8716943646468172,0.9999692013920971,46.59550094604492,0.9284372566707704,0.8717384301514013,-482.0269775390625,0.9314451331496786,0.87192091761356,0.9996920139209707,-482.0269775390625,0.9130355782493194
+8,-1,0.871657897562547,-0.8646595478057861,0.9314207846231083,0.8716909198303173,0.9999384027841941,-0.866702675819397,0.9293619748440078,0.8727048212176527,755.4833374023438,0.9318776037925586,0.8732667402600899,0.9989220487233977,755.4833374023438,0.9329840867700735,0.8716042091699775,45.98941421508789,0.931392096392455,0.8716640713096708,0.9999076041762912,46.117164611816406,0.9316092546065409,0.8716310533662622,-500.8504638671875,0.9314113597246128,0.8716276073125554,1.0,-500.8504638671875,0.9175780640419731
+9,-1,0.8716847417588317,-0.8721379041671753,0.9314361122267485,0.8716943646468172,0.9999692013920971,-0.8721379041671753,0.9269127373142997,0.872677977021368,764.776123046875,0.9318720464241083,0.8731628532974428,0.9990452431550094,766.3433837890625,0.9299146316450253,0.8716847417588317,45.79191970825195,0.9314321781042001,0.8717342856375695,0.9999076041762912,45.79191970825195,0.929184382505271,0.8716310533662622,-472.2821960449219,0.9314113597246128,0.8716276073125554,1.0,-497.92877197265625,0.9154256756951731

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"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f360d99580445075472cdbb7b439e937b9b3a53cdff3b062979db40610e5ef3
+size 498652017

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}