Upload 13 files

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

@@ -1,8 +1,122 @@
 ---
-license: cc-by-3.0
-language:
-- en
-library_name: sentence-transformers
 pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
 ---
-A roberta model further fine-tuned for encoding sentences from the same section in wikipedia articles closer in space. The model was fine-tuned on the training set of wikisection english dataset.
+
+# {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 6708 with parameters:
+```
+{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+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': 32, 'do_lower_case': False}) with Transformer model: RobertaModel 
+  (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": "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,-1,0.688875678312298,0.21451625227928162,0.7007406801162173,0.6340813152632748,0.7830620084141211,0.011116713285446167,0.7527617912617275,0.6873208950673739,446.39990234375,0.7296517172539196,0.6258807617634868,0.8746722760807268,463.9516906738281,0.752832196770017,0.6722151088348272,19.273948669433594,0.6973663671030038,0.5497503691723508,0.9533565026522773,25.77716064453125,0.7326285132766597,0.6885860618254984,47.748291015625,0.700788257678717,0.6322526852714699,0.7859886592280958,1.2547117471694946,0.7602589761489239
+1,-1,0.6977775745381379,0.20492404699325562,0.7134806284713263,0.6432891740333521,0.8008658008658008,0.01354411244392395,0.7591359016016286,0.6690902993719895,335.69403076171875,0.7013278618713948,0.6080418876283815,0.8284250960307298,386.7208557128906,0.7241603451150835,0.6556307542223035,16.894609451293945,0.6970770151636074,0.5897868748681157,0.8520821901103591,18.752403259277344,0.7152351172613437,0.6981129199439059,23.636016845703125,0.71349794909407,0.6433960415441897,0.8007438570818852,1.8228182792663574,0.7716774359749061
+2,-1,0.6902018169623804,0.179021954536438,0.7095585781598304,0.6311053068977799,0.8102859581732821,-0.048351287841796875,0.7566907740053774,0.6613621120663374,340.5686340332031,0.7034177615242224,0.5584829910026168,0.9499420767026401,464.56915283203125,0.7183696833593858,0.6543198585452107,16.773998260498047,0.693946160214757,0.5895643277346747,0.8432412657764771,19.22742462158203,0.710098062689827,0.6899731723675385,21.468889236450195,0.7100117533924565,0.6318041359638698,0.8103164441192611,-6.466011047363281,0.7660399369870547
+3,-1,0.6868940918236693,0.13593482971191406,0.7039844614098033,0.6313141087671763,0.7955612462654716,-0.0446164608001709,0.7513436926039477,0.6648070239619536,364.3100280761719,0.7190925154769113,0.604612987012987,0.8870495701481617,441.24981689453125,0.7237040102988117,0.6609200658496434,17.429285049438477,0.6928780512965995,0.6003977920307506,0.8190354246692275,20.231002807617188,0.7127326391214277,0.6855069812816291,20.047109603881836,0.7042868820604907,0.6283446115587863,0.8011096884336321,-9.032946586608887,0.7599840429875714
+4,-1,0.6790287177611122,0.12285339832305908,0.6975741095468367,0.6221595660796636,0.7937930613986952,-0.08657693862915039,0.7471036028656264,0.6705536247789768,422.10455322265625,0.7195281627838396,0.5868239278086699,0.9297908664105847,477.7283935546875,0.7297992216447178,0.6612249253094323,18.67955780029297,0.6909119826112311,0.611151492414828,0.7946161819401256,21.062088012695312,0.7158698879917538,0.6772757758673251,22.645580291748047,0.6985589225589225,0.6256996718780158,0.7906225230168892,-14.085229873657227,0.7481621125333402
+5,-1,0.6718645204560697,0.1337960958480835,0.6940711254745858,0.6098298589468338,0.8053167489787209,-0.13094359636306763,0.7394516922830743,0.6854307664166819,426.9678955078125,0.7215379685998078,0.6224487539526348,0.858148893360161,468.9588623046875,0.7344527601862045,0.6613468690933479,20.207061767578125,0.6924590016522981,0.548437639099083,0.9390585939881715,26.321395874023438,0.7174525809361008,0.6701420645082616,16.273883819580078,0.6948475724014939,0.6030642230646717,0.8195841716968477,-35.22602081298828,0.7388797703282758
+6,-1,0.6762544966770319,0.14582541584968567,0.6955985407207159,0.6106682027649769,0.8079690262788854,-0.1332850456237793,0.7428792113476992,0.6900341442594964,438.0541076660156,0.720180161524125,0.6257478296073051,0.8481799890250594,478.80511474609375,0.7372861116264031,0.6660874336930674,20.88856315612793,0.7004425809457255,0.5667382864035584,0.916712395585635,25.949804306030273,0.7210590113180488,0.6736174623498568,22.276962280273438,0.6967376917287378,0.6065521915951197,0.8184257057496495,-35.493534088134766,0.7411595217234634
+7,-1,0.6667886104505822,0.09249621629714966,0.6922657589980189,0.613855549529581,0.7936406316688007,-0.11688518524169922,0.7342520760074628,0.6866959331748064,441.6366882324219,0.7141725421849006,0.6298910005589715,0.8244924089994512,483.64276123046875,0.7366585594845865,0.6607219072007804,21.191844940185547,0.7012119567141457,0.5720392013400851,0.9057374550332297,26.606861114501953,0.7193225608617343,0.6650204255838059,22.81573486328125,0.6929348906890106,0.6130909090909091,0.796689226266691,-30.088247299194336,0.7300973533703405
+8,-1,0.6664837509907933,0.10211536288261414,0.6907975298563472,0.6079962915749217,0.7997073349186026,-0.14499104022979736,0.7307157363107932,0.6851563929028718,431.011474609375,0.7106677910715228,0.6258296588535623,0.8221145052130968,485.1802062988281,0.7370754199630012,0.659426254496677,21.681676864624023,0.6997913901005121,0.572470232323624,0.899945125297238,26.773082733154297,0.7186558847939153,0.6642887628803121,18.20148468017578,0.6913789285853837,0.6035474701534963,0.8091274922260838,-42.23976135253906,0.726631100097931
+9,-1,0.6630998109871349,0.12585166096687317,0.6890432923570283,0.6133498263475903,0.7860496311200537,-0.12174004316329956,0.7282460206472967,0.6822754710078653,437.261962890625,0.7058481156659656,0.6234373174436266,0.8133650387171514,488.2479248046875,0.7359740092524213,0.6575208828729956,21.085512161254883,0.6997576090460782,0.575146721102322,0.893299189073837,26.86428451538086,0.717956315362813,0.6615602707152003,20.969688415527344,0.6900005285132921,0.6089035026351383,0.7960185354551552,-36.937259674072266,0.7237710727313599

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 sha256:85a51b49cf59abc469ae56a0129609737eefd48008c71e35962e2400551d0a28
+size 498652017

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32,
+  "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"}