Upload with huggingface_hub

0_SentenceTransformer/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
+}

0_SentenceTransformer/README.md

@@ -0,0 +1,80 @@
+---
+pipeline_tag: sentence-similarity
+license: apache-2.0
+language: 
+  - it
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+---
+
+# sentence-BERTino
+
+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. It was trained on a dataset made from question/context pairs ([squad-it](https://github.com/crux82/squad-it)) and tags/news-article pairs (via scraping). 
+
+## 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 = ["Questo è un esempio di frase", "Questo è un ulteriore esempio"]
+
+model = SentenceTransformer('efederici/sentence-BERTino')
+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 = ["Questo è un esempio di frase", "Questo è un ulteriore esempio"]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('efederici/sentence-BERTino')
+model = AutoModel.from_pretrained('efederici/sentence-BERTino')
+
+# 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)
+```
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (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})
+)
+```

0_SentenceTransformer/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/.cache/torch/sentence_transformers/efederici_sentence-BERTino/",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 3,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "vocab_size": 32102
+}

0_SentenceTransformer/config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.0",
+    "transformers": "4.17.0",
+    "pytorch": "1.10.0+cu111"
+  }
+}

0_SentenceTransformer/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"
+  }
+]

0_SentenceTransformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edeaf53e3122eab7cf32f5f3deaaf2710c440a7b0da5afe4c281673ee0830667
+size 185267017

0_SentenceTransformer/sentence_bert_config.json

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

0_SentenceTransformer/special_tokens_map.json

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

0_SentenceTransformer/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "name_or_path": "/root/.cache/torch/sentence_transformers/efederici_sentence-BERTino/",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

1_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 64, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

1_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239c2707843befbc4780fe214749fc03e0614fdc7e9255dadafe47beae81a24f
+size 197927

README.md

@@ -0,0 +1,91 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 64 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)
+```
+
+
+
+## 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 1724 with parameters:
+```
+{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MSELoss.MSELoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 500,
+    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "eps": 1e-06,
+        "lr": 1e-07
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 100,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): SentenceTransformer(
+    (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+    (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})
+  )
+  (1): Dense({'in_features': 768, 'out_features': 64, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.23.1",
+    "pytorch": "1.12.1+cu113"
+  }
+}

eval/mse_evaluation__results.csv

@@ -0,0 +1,29 @@
+epoch,steps,MSE
+0,500,160.0018858909607
+0,1000,157.27769136428833
+0,1500,155.6653618812561
+0,-1,155.4488182067871
+0,500,98.15781712532043
+0,1000,76.94787383079529
+0,1500,68.42235922813416
+0,-1,66.3095772266388
+1,500,63.229817152023315
+1,1000,61.31596565246582
+1,1500,60.14971137046814
+1,-1,59.68950390815735
+2,500,59.01828408241272
+2,1000,58.600419759750366
+2,1500,58.39851498603821
+2,-1,58.3707332611084
+0,500,58.216989040374756
+0,1000,58.06503891944885
+0,1500,57.93534517288208
+0,-1,57.89196491241455
+1,500,57.828253507614136
+1,1000,57.760089635849
+1,1500,57.728540897369385
+1,-1,57.72488713264465
+0,500,57.713496685028076
+0,1000,57.70211219787598
+0,1500,57.697200775146484
+0,-1,57.69643187522888

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,29 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,500,0.5865738040483492,0.6080073489584343,0.6135697139081404,0.6209144397277622,0.6080297443609035,0.6150423947449148,0.30760717559007184,0.31234556074873465
+0,1000,0.5932329861734787,0.6145486559695778,0.6209473347843074,0.6285679752654623,0.6156857991443561,0.6230859536837934,0.2902995170696891,0.29410016166955844
+0,1500,0.5997207615500473,0.6197545563640058,0.6266288668984643,0.6333906867830073,0.6216103921025053,0.6283979609131071,0.29927639170944115,0.3039065427395013
+0,-1,0.6004929935405958,0.6203905760382272,0.6272614520062297,0.634024206793723,0.622256060456697,0.6291191927282038,0.3009699947338997,0.3056782821262222
+0,500,0.6082876631364406,0.6383080638463929,0.6713194802395258,0.6666769766877335,0.6696520375976636,0.6676769987310615,0.4984370002871881,0.48647455814121354
+0,1000,0.6695328825953906,0.6838212732319437,0.7159880183243681,0.7080623220109675,0.7104452645368556,0.7043184333029457,0.6001198237468279,0.5904204021173427
+0,1500,0.6938622625314218,0.7027819962982079,0.7300484668389849,0.7227559033386031,0.7239534109735188,0.7171358229426745,0.6432735292808788,0.6345696105211257
+0,-1,0.6942694267356905,0.7037752140663714,0.7307942823803945,0.7232597720141782,0.7239209364944754,0.7174398302701811,0.6447556662871575,0.6365812702723829
+1,500,0.7026776271111842,0.7103170015048932,0.7351407131757489,0.7278891702308841,0.7283502666392208,0.7219225344353434,0.6598208883116933,0.6523325409289799
+1,1000,0.7051954773480473,0.712368926410317,0.7357815021563106,0.7286132668166436,0.7292599158711848,0.7226115402495245,0.6661954715118892,0.6596294534379665
+1,1500,0.7082188011794502,0.7152173340725155,0.7378006755328732,0.7308711900850527,0.7315619929431638,0.7252391043427502,0.6710356608646818,0.6647982399231508
+1,-1,0.70904626023681,0.7157006511324661,0.7386734692835749,0.7315364734629127,0.7322374623337847,0.7257611918921245,0.6716495784644925,0.6648813111548563
+2,500,0.7100771821625964,0.7167180521913615,0.7391966431541905,0.7324477676869227,0.7327015552647981,0.7262537331577372,0.6736893242334752,0.667143259335068
+2,1000,0.7108737865640337,0.7169675381288808,0.7395318432365394,0.7325689012225832,0.7331158055268099,0.726662598208946,0.6749191654461464,0.6684612228780606
+2,1500,0.7117215803275778,0.7177861472354646,0.7399094584535856,0.7329357199813928,0.7336377259374134,0.7272406822382951,0.6764804931321545,0.6700393218318923
+2,-1,0.711675752291452,0.71773214541879,0.7398356721932455,0.7328735135327141,0.7335426460029394,0.7271314488233886,0.6764356227769781,0.6698884267099644
+0,500,0.7121460455239379,0.7181123574252887,0.7399511395506606,0.7331083588907218,0.7336774177428855,0.7272558299355949,0.6771142222790999,0.6705752866145787
+0,1000,0.7123861478820172,0.7181627442194691,0.7400716088926611,0.7330949496287871,0.7338919056678781,0.727296143130711,0.6775155455308138,0.6708743366430204
+0,1500,0.7122284907285029,0.7180972453152019,0.7401198061461532,0.7332444924367473,0.7337385450265813,0.7272772676728283,0.6771726702603322,0.6703615444741903
+0,-1,0.7120537711301091,0.7179151099580299,0.739928382899804,0.7328671734324397,0.7336732597926334,0.7270930896096183,0.6770149506244509,0.6703754003556386
+1,500,0.712251279207934,0.7180605495603078,0.7399009046552868,0.7328821274176701,0.7337147222065724,0.7271828049741026,0.6775682024150373,0.6710392299952491
+1,1000,0.7125332144097017,0.7182585034337489,0.7401266535032988,0.7332453749996348,0.7339200062049424,0.7273773976352566,0.6778856175804594,0.6712869419099701
+1,1500,0.7126742859770369,0.7183989294362636,0.740284929037369,0.7333443804061257,0.7340499087406678,0.7274551307850554,0.6779089373279104,0.6712837070322928
+1,-1,0.712748264487567,0.7184477986871575,0.7403131695377074,0.7333492451781706,0.7340709425847874,0.7274524030251635,0.6779903965891169,0.6714038352290735
+0,500,0.7126967895258003,0.7184174555008799,0.7402840486509272,0.733308238032397,0.7340461198296704,0.7274432339796818,0.6779725544896934,0.6713037515301116
+0,1000,0.712916278926716,0.7186633827170787,0.7404429389807402,0.7335128164655754,0.7342023524428132,0.727619871112414,0.678277663787251,0.6716970293815879
+0,1500,0.7128783807214034,0.7186522314638217,0.7404290748112105,0.7334913484792108,0.7341734466453587,0.727559420892707,0.6782398243891938,0.6716509314850065
+0,-1,0.712884474626804,0.7186568382285708,0.7404293672433467,0.7334823929570085,0.7341750526470242,0.7275848746469504,0.678234793119852,0.6716365702651312

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "0_SentenceTransformer",
+    "type": "sentence_transformers.SentenceTransformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]