first commit

model/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
+}

model/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
+
+
+#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 2301 with parameters:
+```
+{'batch_size': None, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'nkwdataset.BatchNegSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 100,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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 -->

model/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "aubmindlab/bert-base-arabertv02",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

model/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.27.4",
+    "pytorch": "2.0.0+cu117"
+  }
+}

model/eval/similarity_evaluation_results.csv

@@ -0,0 +1,25 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,100,-0.0014084016071803707,-0.005974646349259352,-0.0011148677844655234,-0.006823761697462621,-0.0031921576983014958,-0.008462784423718384,-0.0013527167022492263,-0.006134298479750079
+0,200,-0.01439619727472125,-0.015789587420051498,-0.012616585674178301,-0.015161242838654849,-0.014894045645202003,-0.018851901064299167,-0.01659789702901683,-0.017743234505539794
+0,300,-0.008738723873515358,-0.0100447544643897,-0.009797046327609193,-0.014052737089441053,-0.009526474602157036,-0.011658422628695866,-0.009112346677298289,-0.009101418491561469
+0,400,-0.01313536882963247,-0.014598666539196383,-0.01593316328197991,-0.01811629200418959,-0.01672933061385762,-0.01799174910465491,-0.013151743118259781,-0.01439967997381517
+0,500,-0.008869364236502473,-0.008790614520590231,-0.010174086262157392,-0.01022940726438435,-0.010878016135249292,-0.010369907390132294,-0.008818899113654025,-0.008713625544425613
+0,600,-0.01363836263409382,-0.011750128164693528,-0.015303395037270587,-0.01412679926768333,-0.01703749699271561,-0.01486509395290605,-0.015494911088842647,-0.013471547951506135
+0,700,-0.014600459643236731,-0.014662057250647436,-0.017164554205655037,-0.016331025037158265,-0.017270337006921908,-0.017400432885208553,-0.014055988281518,-0.014777249256824762
+0,800,-0.014444018529123652,-0.014322977178515894,-0.016619473259190404,-0.017732101068072995,-0.014759393356356036,-0.014067118977203093,-0.014187340072441176,-0.014168537092308909
+0,900,-0.012059366161042934,-0.00946247318806493,-0.013230994399252573,-0.012596806198439644,-0.015186059366421829,-0.01256792834710906,-0.010968171115246207,-0.009087741877910121
+0,1000,-0.016443943331842334,-0.01595262486862947,-0.019305602087822143,-0.01957981682054613,-0.017488193995684364,-0.015245016038582321,-0.017474747265768326,-0.01612494672066406
+0,1100,-0.020416071728638133,-0.02148368288162378,-0.021261296776430773,-0.024522533165576222,-0.020594486767758848,-0.020248150965082434,-0.0208427323676512,-0.021081160640394538
+0,1200,-0.017012769979586274,-0.016410660138166833,-0.019394052196309144,-0.019055085926952306,-0.02010393619340861,-0.017694564214127836,-0.017026481886912043,-0.016061502585886536
+0,1300,-0.013486619942277862,-0.012099696435853461,-0.015135997923372509,-0.015821911853236614,-0.017733783338205085,-0.015674052236071614,-0.013124888965812546,-0.012261346698411378
+0,1400,-0.014441627263798508,-0.011455310368016792,-0.015927679742322686,-0.015247395943780537,-0.016586389912067852,-0.012854957288182142,-0.014352019025621271,-0.0113602548307323
+0,1500,-0.02077603461024176,-0.01710888452574343,-0.019979384928271213,-0.021134742597521836,-0.022214899094120978,-0.0165309200178185,-0.020667259854019248,-0.01742850041980119
+0,1600,-0.02198034359783125,-0.02119235835883809,-0.02243668213380327,-0.02359528327966424,-0.021657520619871418,-0.019147644113161326,-0.02240726677808149,-0.021254780447558932
+0,1700,-0.020417976276599283,-0.016966399859052565,-0.02095824982049848,-0.021055550786257607,-0.02195026237359019,-0.017707957897320572,-0.020353056162476957,-0.016732389555688888
+0,1800,-0.020990097092713357,-0.01911667438317952,-0.02172250613608771,-0.022940819572541866,-0.022214673669246003,-0.018708375874130656,-0.020740607214797924,-0.018620962268669983
+0,1900,-0.021400268891744206,-0.017907803727339883,-0.02155435083718565,-0.021807415114090713,-0.02165165545936554,-0.01766511672327363,-0.020884045931872916,-0.017178921483798574
+0,2000,-0.0206320959150904,-0.01787171265489736,-0.0221929530985392,-0.021354589346700287,-0.021605489099969614,-0.01814777376481024,-0.02039922693742446,-0.01783710600153296
+0,2100,-0.019802237769944137,-0.016445749043551332,-0.020892064963634077,-0.02024704449503452,-0.020499812514340496,-0.017191359154443267,-0.01991631913362716,-0.016848062506809428
+0,2200,-0.01939068287472302,-0.014535049360356227,-0.02020889988479752,-0.018989008603544237,-0.020027487013542136,-0.01539548588862228,-0.019217594681193696,-0.01451343654992022
+0,2300,-0.019515997505572594,-0.01445528622513276,-0.020416274630010528,-0.018983438147986097,-0.020459416083599302,-0.015753158839636242,-0.01935326935442082,-0.014398178058104286
+0,-1,-0.019516074040339688,-0.01445404042532921,-0.02041634605574272,-0.018983085613887368,-0.020459412230105216,-0.01575297396948282,-0.01935335432409336,-0.014399991239273631

model/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"
+  }
+]

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd99a84a7b0b8d74d212f8e9f29a3c7b86f3185948b490afe389eed25c194a43
+size 540844589

model/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 1024,
+  "do_lower_case": false
+}

model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

model/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}